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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rethink
    -0.07
    高清
    -0.06
    WAR
    -0.06
    Ch
    -0.06
    이자
    -0.06
    гов
    -0.06
     Wake
    -0.06
     yarat
    -0.06
     проис
    -0.06
     bury
    -0.06
    POSITIVE LOGITS
     قي
    0.08
    195
    0.07
    binding
    0.07
    dense
    0.06
    covered
    0.06
    199
    0.06
    esel
    0.06
    utherford
    0.06
    investment
    0.06
     }
↵
↵
    0.06
    Act Density 0.000%

    No Known Activations