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

    Neuronpedia

    INDEX
    Explanations

    utf

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (reordered
    -0.07
     amplifier
    -0.07
     pz
    -0.06
    été
    -0.06
     cheese
    -0.06
     feast
    -0.06
    -Fi
    -0.06
    :H
    -0.06
    онт
    -0.06
     Credentials
    -0.06
    POSITIVE LOGITS
    _UINT
    0.07
     Qur
    0.06
    HttpPost
    0.06
     />}
    0.06
     IsNot
    0.06
    BOTTOM
    0.06
    _GR
    0.06
     */}↵
    0.06
    /man
    0.06
     populist
    0.06
    Act Density 0.001%

    No Known Activations