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

    Neuronpedia

    INDEX
    Explanations

    code examples

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    entity
    -0.07
     보면
    -0.06
     obra
    -0.06
     power
    -0.06
     Dota
    -0.06
    кий
    -0.06
    TimeStamp
    -0.06
     muz
    -0.06
    udent
    -0.05
     puss
    -0.05
    POSITIVE LOGITS
    xFC
    0.07
    Michigan
    0.07
    ypress
    0.07
    ανδ
    0.07
     być
    0.07
    (pad
    0.07
     ситуации
    0.06
    (module
    0.06
     outsider
    0.06
    :m
    0.06
    Act Density 0.062%

    No Known Activations