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

    Neuronpedia

    INDEX
    Explanations

    future plans and intentions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     immortal
    -0.07
    忒
    -0.07
    Agregar
    -0.07
    垕
    -0.07
    Tp
    -0.07
     Ao
    -0.07
     arou
    -0.07
     doctrines
    -0.07
    lod
    -0.07
     Fare
    -0.07
    POSITIVE LOGITS
    �
    0.07
     means
    0.07
     numerical
    0.07
     choose
    0.07
    周边
    0.07
     respectful
    0.07
     chose
    0.06
    行贿
    0.06
    משפחה
    0.06
     seçil
    0.06
    Act Density 0.060%

    No Known Activations