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

    Neuronpedia

    INDEX
    Explanations

    озв

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bushes
    -0.07
    repeat
    -0.07
    includes
    -0.07
    chet
    -0.06
    -first
    -0.06
     Forrest
    -0.06
     Marin
    -0.06
     Moj
    -0.06
    (nd
    -0.06
    kad
    -0.06
    POSITIVE LOGITS
    озв
    0.10
    own
    0.07
    üyoruz
    0.07
    vvm
    0.06
     Cathy
    0.06
    ะแ
    0.06
    842
    0.06
    ymoon
    0.06
     indust
    0.06
    -generator
    0.06
    Act Density 0.001%

    No Known Activations