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

    Neuronpedia

    INDEX
    Explanations

    work

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    onna
    -0.07
    Examples
    -0.07
    Silver
    -0.07
     endDate
    -0.07
    deal
    -0.07
     kron
    -0.07
    송
    -0.07
    radius
    -0.06
     coupling
    -0.06
    ฉ
    -0.06
    POSITIVE LOGITS
    ;c
    0.07
     Не
    0.07
    .equals
    0.06
     qualifying
    0.06
    _BUCKET
    0.06
     fontWithName
    0.06
    .**************↵
    0.06
    itbart
    0.06
    토토
    0.06
     =>
↵
    0.06
    Act Density 0.024%

    No Known Activations