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

    Neuronpedia

    INDEX
    Explanations

    games and assessment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     worsening
    -0.07
    eldom
    -0.07
    digital
    -0.07
    creds
    -0.06
     rapport
    -0.06
    -${
    -0.06
    commons
    -0.06
    constructed
    -0.06
     confidential
    -0.06
    Construct
    -0.06
    POSITIVE LOGITS
     مج
    0.07
    ================================================================================
    0.07
     >>↵↵
    0.07
    ोष
    0.06
    、今
    0.06
    操作
    0.06
    =__
    0.06
    继续
    0.06
     src
    0.06
    _play
    0.06
    Act Density 0.001%

    No Known Activations