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

    Neuronpedia

    INDEX
    Explanations

    Android code and related words and also fantasy-genre words

    oai_token-act-pair · gemini-2.0-flash

    Android app layout

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     "
    -0.81
     '
    -0.78
     P
    -0.78
     B
    -0.69
     ‘
    -0.67
    <eos>
    -0.66
     M
    -0.66
     I
    -0.66
     _
    -0.66
     -
    -0.66
    POSITIVE LOGITS
     Majefty
    1.44
     pleaſure
    1.41
     myſelf
    1.35
     Anſ
    1.34
    GraphicsUnit
    1.30
     Efq
    1.30
     raiſ
    1.27
     Theſe
    1.25
     Houſe
    1.24
     Jefus
    1.23
    Act Density 0.092%

    No Known Activations