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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Rockefeller
    -0.07
    르
    -0.06
    -summary
    -0.06
    /perl
    -0.06
     molto
    -0.06
    _ticket
    -0.06
    ями
    -0.06
     dai
    -0.06
     gest
    -0.06
     Biom
    -0.06
    POSITIVE LOGITS
    bank
    0.07
     sợ
    0.06
    ific
    0.06
     smack
    0.06
    ivalence
    0.06
     bloc
    0.06
    .jackson
    0.06
    ・・・
    0.06
    ิม
    0.06
     compan
    0.06
    Act Density 0.020%

    No Known Activations