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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Members
    -0.08
     diagnosis
    -0.08
    IVER
    -0.08
     suicide
    -0.07
    'aide
    -0.07
    Loader
    -0.07
    Speaker
    -0.07
    Description
    -0.07
    VH
    -0.07
     Vo
    -0.07
    POSITIVE LOGITS
     recurse
    0.09
     recursive
    0.09
     Geschichten
    0.08
    odra
    0.08
     spawn
    0.08
    )n
    0.08
    antoor
    0.08
     ప్రతి
    0.08
     రంగ
    0.08
    akav
    0.08
    Act Density 0.088%

    No Known Activations