Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    instances of the name "Peter" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Appears before or after "Peter" or a similar short name

    np_acts-logits-general · gemini-2.0-flash

    peter followed by a name

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.65
     whole
    -0.53
    whole
    -0.52
    prnewswire
    -0.49
    olsom
    -0.49
    PROLOG
    -0.49
     JsonConvert
    -0.48
     saites
    -0.48
    jahteraan
    -0.46
     clo
    -0.46
    POSITIVE LOGITS
    MessageOf
    0.73
    LayoutPanel
    0.65
    borough
    0.64
    bilt
    0.61
    dymyr
    0.60
    DoubleQuotes
    0.58
    assertNull
    0.54
     protoimpl
    0.54
    appcompat
    0.54
    __).
    0.53
    Act Density 0.107%

    No Known Activations