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

    Neuronpedia

    INDEX
    Explanations

    or

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    358
    -0.07
     مش
    -0.07
     gorge
    -0.06
     Terminal
    -0.06
     كبير
    -0.06
    arehouse
    -0.06
    cams
    -0.06
    .mongodb
    -0.06
     dveře
    -0.06
    genus
    -0.06
    POSITIVE LOGITS
    acular
    0.08
    _ANT
    0.07
    UILabel
    0.07
    azaar
    0.06
     ^↵
    0.06
    _UNDEF
    0.06
     alph
    0.06
    소년
    0.06
    нию
    0.06
     owned
    0.06
    Act Density 0.003%

    No Known Activations