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

    Neuronpedia

    INDEX
    Explanations

    checkpoint

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     науч
    -0.06
     kde
    -0.06
    ,function
    -0.06
    προ
    -0.06
     diversas
    -0.06
    atég
    -0.06
     مشتر
    -0.06
    OCK
    -0.06
    διά
    -0.06
    astype
    -0.06
    POSITIVE LOGITS
     Haram
    0.10
     checkpoint
    0.08
    _SUPPORTED
    0.07
    .disconnect
    0.07
    ิ
    0.07
    Them
    0.06
     copy
    0.06
    inox
    0.06
     updater
    0.06
    zej
    0.06
    Act Density 0.001%

    No Known Activations