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

    Neuronpedia

    INDEX
    Explanations

    Inappropriate/offensive topics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     prostředí
    -0.07
    friendly
    -0.06
    "]
    -0.06
     freezes
    -0.06
     Sandy
    -0.06
     ویر
    -0.06
    струк
    -0.06
     ceremony
    -0.06
    cw
    -0.06
     Shade
    -0.06
    POSITIVE LOGITS
    ovol
    0.07
     Switzerland
    0.07
    Sweden
    0.07
    GEST
    0.06
     acceptable
    0.06
    _dn
    0.06
    ONUS
    0.06
    -detail
    0.06
    异
    0.06
    ETS
    0.06
    Act Density 0.017%

    No Known Activations