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

    Neuronpedia

    INDEX
    Explanations

    USSR

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    关心
    -0.07
     ted
    -0.07
     Days
    -0.07
    rid
    -0.07
    ndx
    -0.07
    Dos
    -0.07
    agnostic
    -0.07
    Camp
    -0.07
     pale
    -0.06
    cke
    -0.06
    POSITIVE LOGITS
     kvinne
    0.08
     devastation
    0.08
     Overwatch
    0.07
     обор
    0.07
    }],↵
    0.07
    士兵
    0.07
    𝕸
    0.07
     tragedies
    0.07
    影音
    0.07
    .MOD
    0.06
    Act Density 0.005%

    No Known Activations