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

    Neuronpedia

    INDEX
    Explanations

    XML configuration files

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .notifications
    -0.07
    ера
    -0.07
     Walters
    -0.07
    quis
    -0.06
    iT
    -0.06
    غر
    -0.06
    Van
    -0.06
    _star
    -0.06
    })",
    -0.06
    妮
    -0.06
    POSITIVE LOGITS
     caster
    0.07
     громад
    0.06
     sculpt
    0.06
    pek
    0.06
    選
    0.06
    Device
    0.06
     hrd
    0.06
    ूबर
    0.06
     spilled
    0.06
    ypress
    0.06
    Act Density 0.006%

    No Known Activations