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

    Neuronpedia

    INDEX
    Explanations

    Code and URLs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ocal
    -0.07
     Scatter
    -0.07
     grasp
    -0.06
     governors
    -0.06
    Tour
    -0.06
    ariance
    -0.06
    uss
    -0.06
     też
    -0.06
    IALIZED
    -0.06
     kindly
    -0.06
    POSITIVE LOGITS
     needed
    0.07
    quality
    0.07
    (Member
    0.06
     UNITED
    0.06
    .authenticate
    0.06
     милли
    0.06
     washington
    0.06
    þ
    0.06
    ')));↵
    0.06
    _MISS
    0.06
    Act Density 0.000%

    No Known Activations