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

    Neuronpedia

    INDEX
    Explanations

    exclamations such as "oh"

    oai_token-act-pair · gemini-2.0-flash

    Oh

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    taz
    -0.45
    expandindo
    -0.44
    Ecotoxicity
    -0.42
     God
    -0.42
    atorium
    -0.40
    onato
    -0.40
     He
    -0.40
    imageshack
    -0.40
    star
    -0.40
    astes
    -0.40
    POSITIVE LOGITS
    +#+#
    0.80
    BufferException
    0.78
    DockStyle
    0.77
    endphp
    0.73
    MLLoader
    0.72
     estekak
    0.68
     avoient
    0.65
    Viitteet
    0.65
     NgModule
    0.64
    клопе
    0.64
    Act Density 0.879%

    No Known Activations