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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    fen
    -0.07
     như
    -0.07
     길
    -0.07
     newbie
    -0.07
    iben
    -0.06
     vines
    -0.06
    coll
    -0.06
    tax
    -0.06
    _energy
    -0.06
    ови
    -0.06
    POSITIVE LOGITS
     birinci
    0.06
    μφ
    0.06
    .invokeLater
    0.06
    aporation
    0.06
    .app
    0.06
    ElementsByTagName
    0.06
    _DELETE
    0.06
     make
    0.06
     experimentation
    0.06
     unter
    0.06
    Act Density 0.096%

    No Known Activations