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

    Neuronpedia

    INDEX
    Explanations

    violent

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ΕΙΣ
    -0.07
    _OD
    -0.07
     Fon
    -0.06
    üle
    -0.06
     giorn
    -0.06
    ารย
    -0.06
     oo
    -0.06
    CONDS
    -0.06
    ++↵
    -0.06
     pee
    -0.06
    POSITIVE LOGITS
     intimate
    0.07
    icle
    0.07
     NUITKA
    0.07
    SetBranch
    0.06
     Twig
    0.06
    EmptyEntries
    0.06
    violent
    0.06
     laboratory
    0.06
    Late
    0.06
     carrier
    0.06
    Act Density 0.005%

    No Known Activations