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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    еш
    -0.06
     CSC
    -0.06
    indh
    -0.06
     Drops
    -0.06
    `;↵
    -0.06
    zeichnet
    -0.06
     و
    -0.06
    из
    -0.06
    ulated
    -0.06
    Effective
    -0.06
    POSITIVE LOGITS
     fetisch
    0.08
    -byte
    0.06
    गढ
    0.06
    rvé
    0.06
    -controls
    0.06
     sistem
    0.06
    xAE
    0.06
     File
    0.06
    _ComCallableWrapper
    0.06
    _lift
    0.06
    Act Density 0.111%

    No Known Activations