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

    Neuronpedia

    INDEX
    Explanations

    questions or phrases that seek clarification or understanding

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

    what is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    endphp
    -0.59
    EndContext
    -0.57
     betweenstory
    -0.54
    bcryptjs
    -0.52
    meneu
    -0.48
    AccessorTable
    -0.47
    HCM
    -0.46
    InputBorder
    -0.45
    HTC
    -0.45
    Bioaccumulative
    -0.44
    POSITIVE LOGITS
     the
    0.69
     a
    0.48
     different
    0.46
     alternative
    0.45
     additional
    0.44
     an
    0.44
     this
    0.42
     modifications
    0.41
    setcounter
    0.41
     exceptions
    0.40
    Act Density 0.040%

    No Known Activations