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

    Neuronpedia

    INDEX
    Explanations

    usage

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    10
    -0.08
    11
    -0.08
    .CharField
    -0.07
    fol
    -0.07
    setDefault
    -0.07
    _filt
    -0.07
    14
    -0.06
     "@
    -0.06
    Pod
    -0.06
    60
    -0.06
    POSITIVE LOGITS
     usage
    0.15
    age
    0.09
     Usage
    0.09
     dependency
    0.09
    acy
    0.08
    AGE
    0.08
    ạc
    0.08
     dosage
    0.08
     요
    0.08
     Huss
    0.08
    Act Density 0.015%

    No Known Activations