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

    Neuronpedia

    INDEX
    Explanations

    text between vertical bars, often used to denote absolute value

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    pery
    -0.08
    rema
    -0.07
    dsl
    -0.06
    âĶģâĶģâĶģâĶģâĶģâĶģâĶģâĶģâĶģâĶģâĶģâĶģâĶģâĶģâĶģâĶģ
    -0.06
    emme
    -0.06
    unks
    -0.06
    preter
    -0.06
    äºŃ
    -0.06
    å¦ĥ
    -0.06
    extr
    -0.06
    POSITIVE LOGITS
    a
    0.07
    onne
    0.06
    vette
    0.06
    amage
    0.06
     bart
    0.06
    .|
    0.06
     fest
    0.06
    batch
    0.06
     barg
    0.06
     sign
    0.06
    Act Density 0.181%

    No Known Activations