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

    Neuronpedia

    INDEX
    Explanations

    Common English words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Pu
    -0.07
     мир
    -0.07
     page
    -0.06
    amu
    -0.06
    Sans
    -0.06
    svp
    -0.06
    icot
    -0.06
    Integration
    -0.06
    imen
    -0.06
     loser
    -0.06
    POSITIVE LOGITS
    ].
    0.07
    θεν
    0.06
    ,callback
    0.06
    ulent
    0.06
    `.
    0.06
    <Event
    0.06
     searchable
    0.06
    ,cv
    0.06
    けない
    0.06
    .getRequest
    0.06
    Act Density 0.030%

    No Known Activations