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

    Neuronpedia

    INDEX
    Explanations

    standalone

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Attack
    -0.06
    secret
    -0.06
    .left
    -0.06
     subject
    -0.06
    .MaxLength
    -0.06
     Scientists
    -0.06
    ots
    -0.06
    ecurity
    -0.06
     priest
    -0.06
     Providing
    -0.06
    POSITIVE LOGITS
     standalone
    0.09
    andalone
    0.08
    ohn
    0.07
    Tac
    0.07
    CLUDE
    0.07
    -alone
    0.07
    plet
    0.07
    _pw
    0.06
    ‚ط
    0.06
     titleLabel
    0.06
    Act Density 0.003%

    No Known Activations