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

    Neuronpedia

    INDEX
    Explanations

    words ending in "estimate" or "ating", often following a word starting with "esti" or phrases that contain "the"

    oai_token-act-pair · gemini-2.0-flash

    estimates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <bos>
    -0.47
    ganu
    -0.45
    punkt
    -0.45
    што
    -0.42
      
    -0.42
    TAGS
    -0.42
     sõ
    -0.41
    SOLUTION
    -0.41
    fattning
    -0.41
     Ne
    -0.40
    POSITIVE LOGITS
    makeConstraints
    0.84
     BorderRadius
    0.84
     AdapterView
    0.77
    LayoutPanel
    0.77
     resourceCulture
    0.73
    ArgsConstructor
    0.73
     intptr
    0.71
    ContentAlignment
    0.70
    IsContent
    0.70
     BoxFit
    0.70
    Act Density 1.560%

    No Known Activations