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

    Neuronpedia

    INDEX
    Explanations

    breaking

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     apprent
    -0.08
     Vz
    -0.07
    /theme
    -0.07
    )paren
    -0.07
    —it
    -0.07
     subdued
    -0.07
    �
    -0.06
     рабо
    -0.06
     burned
    -0.06
     b
    -0.06
    POSITIVE LOGITS
    610
    0.08
    idue
    0.06
    byte
    0.06
    τηγορία
    0.06
     Pregnancy
    0.06
     Shares
    0.06
     signals
    0.06
    뢰
    0.06
     Osc
    0.06
     Berry
    0.06
    Act Density 0.008%

    No Known Activations