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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dist
    -0.06
     vanilla
    -0.06
     Tell
    -0.06
     evoke
    -0.06
    ynchronized
    -0.06
     Case
    -0.06
     Sat
    -0.06
     Circle
    -0.06
    (meta
    -0.05
    602
    -0.05
    POSITIVE LOGITS
     Boris
    0.08
    ду
    0.07
     partager
    0.06
    'M
    0.06
    Cut
    0.06
     inher
    0.06
     implicated
    0.06
    登
    0.06
     فيه
    0.06
    你们
    0.06
    Act Density 0.070%

    No Known Activations