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

    Neuronpedia

    INDEX
    Explanations

    already

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ز
    -0.07
     evaluator
    -0.07
     enrichment
    -0.07
    abort
    -0.07
     近
    -0.07
    acz
    -0.07
     conductivity
    -0.07
    ada
    -0.06
     persecution
    -0.06
     Rename
    -0.06
    POSITIVE LOGITS
    _EXPORT
    0.06
    -away
    0.06
    ализации
    0.06
    positories
    0.06
     SELECT
    0.06
    -details
    0.05
    0.05
    _predict
    0.05
    _Response
    0.05
    -scal
    0.05
    Act Density 0.059%

    No Known Activations