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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .progress
    -0.07
     Vault
    -0.06
     fellows
    -0.06
     б
    -0.06
     rails
    -0.06
     melt
    -0.06
     blocks
    -0.06
     ank
    -0.06
    445
    -0.06
    	step
    -0.06
    POSITIVE LOGITS
    .concat
    0.07
    Parse
    0.06
    quartered
    0.06
    UV
    0.06
    DBObject
    0.06
    Edge
    0.06
     ケ
    0.06
    .freeze
    0.06
    _softmax
    0.06
    เบ
    0.06
    Act Density 0.000%

    No Known Activations