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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    бут
    -0.08
     greedy
    -0.07
     participated
    -0.07
     handshake
    -0.06
     prev
    -0.06
     frag
    -0.06
    ϊκ
    -0.06
    olia
    -0.06
     reporters
    -0.06
    ак
    -0.06
    POSITIVE LOGITS
    \/\/
    0.07
    ΙΟ
    0.06
    iterr
    0.06
    *</
    0.06
    ..:
    0.06
     Living
    0.06
    -Life
    0.06
    Erreur
    0.06
    KW
    0.06
     errorHandler
    0.06
    Act Density 0.000%

    No Known Activations