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

    Neuronpedia

    INDEX
    Explanations

    Fifth

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     crowds
    -0.06
     реги
    -0.06
    .class
    -0.06
     trumpet
    -0.06
    听到
    -0.06
    romium
    -0.06
    .thread
    -0.06
    .invoice
    -0.06
     class
    -0.06
    ecret
    -0.06
    POSITIVE LOGITS
     thỏa
    0.07
     합
    0.06
    antwort
    0.06
     �
    0.06
     Бер
    0.06
    询
    0.06
    icha
    0.06
    bias
    0.06
    461
    0.06
    385
    0.06
    Act Density 0.001%

    No Known Activations