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

    Neuronpedia

    INDEX
    Explanations

    scientific contexts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ^(@)
    -0.97
     Efq
    -0.96
     esternos
    -0.94
    ſelf
    -0.93
     purpoſe
    -0.93
     Theſe
    -0.92
     myſelf
    -0.87
    windowFixed
    -0.85
    JspWriter
    -0.85
     raiſ
    -0.85
    POSITIVE LOGITS
     (
    0.55
    ine
    0.55
    <eos>
    0.47
     P
    0.46
    ce
    0.46
    ↵
    0.46
    (
    0.44
    v
    0.44
     '
    0.44
    p
    0.44
    Act Density 0.028%

    No Known Activations