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

    Neuronpedia

    INDEX
    Explanations

    when

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hashlib
    -0.07
     chooser
    -0.06
     neigh
    -0.06
    ']}'
    -0.06
     pdb
    -0.06
    UiThread
    -0.06
     DISABLE
    -0.06
    _blend
    -0.06
    梯
    -0.06
     Lexus
    -0.06
    POSITIVE LOGITS
     encouragement
    0.07
     recognizing
    0.07
     launching
    0.07
     identify
    0.06
     Cherry
    0.06
     purely
    0.06
    .Player
    0.06
     WALL
    0.06
     opposition
    0.06
     Verify
    0.06
    Act Density 0.003%

    No Known Activations