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

    Neuronpedia

    INDEX
    Explanations

    Rev/Reviews

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    коп
    -0.07
    -env
    -0.07
    已经在
    -0.07
    ზ
    -0.07
    zip
    -0.07
    nız
    -0.06
     cough
    -0.06
     convincing
    -0.06
     Oscar
    -0.06
    Ear
    -0.06
    POSITIVE LOGITS
    aned
    0.08
    势必
    0.07
     chlorine
    0.07
    正因为
    0.07
    わた
    0.07
    :Int
    0.07
     ARG
    0.07
    เทคโนโลย
    0.07
    /../
    0.06
    __);↵↵
    0.06
    Act Density 0.000%

    No Known Activations