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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Wenger
    -0.08
    _movie
    -0.07
    ith
    -0.07
     MediaQuery
    -0.06
     Launcher
    -0.06
     geometric
    -0.06
     Catal
    -0.06
    _exists
    -0.06
    inter
    -0.06
     OMIT
    -0.06
    POSITIVE LOGITS
    .errors
    0.07
     ncols
    0.06
    /tasks
    0.06
     consistent
    0.06
    гля
    0.06
    idade
    0.06
    .water
    0.06
     Nurse
    0.06
    modules
    0.06
     wave
    0.06
    Act Density 0.030%

    No Known Activations