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

    Neuronpedia

    INDEX
    Explanations

    Times of day

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    公益
    -0.07
    AGING
    -0.07
    讦
    -0.07
    を選
    -0.06
    Dos
    -0.06
    )?↵↵
    -0.06
    learning
    -0.06
     автом
    -0.06
    AuthToken
    -0.06
    Alert
    -0.06
    POSITIVE LOGITS
    grand
    0.07
     Presidency
    0.07
     higher
    0.07
     hairy
    0.07
    arehouse
    0.07
    *******
    0.07
    _slope
    0.07
    ',...↵
    0.07
    tre
    0.06
    ⋯
    0.06
    Act Density 0.005%

    No Known Activations