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

    Neuronpedia

    INDEX
    Explanations

    data manipulation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .getAmount
    -0.07
    gp
    -0.07
    ynomials
    -0.07
     край
    -0.07
    럼
    -0.06
     personalities
    -0.06
    _tolerance
    -0.06
     Arms
    -0.06
     aks
    -0.06
     Charg
    -0.06
    POSITIVE LOGITS
    tiv
    0.06
    ubre
    0.06
    ائية
    0.06
     افت
    0.06
    iq
    0.06
    ým
    0.06
     velké
    0.06
     القي
    0.06
     freeway
    0.06
     příspěv
    0.06
    Act Density 0.014%

    No Known Activations