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

    Neuronpedia

    INDEX
    Explanations

    trial

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cases
    -0.06
     languages
    -0.06
    nictví
    -0.06
    farm
    -0.06
     favour
    -0.06
     puff
    -0.06
    Anything
    -0.06
    mant
    -0.06
     kuvvet
    -0.06
    UNT
    -0.06
    POSITIVE LOGITS
    ักเร
    0.07
    浩
    0.07
     Pharmac
    0.07
    ertility
    0.07
    ror
    0.06
     Trim
    0.06
    _event
    0.06
    łem
    0.06
     QGraphics
    0.06
    irected
    0.06
    Act Density 0.003%

    No Known Activations