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

    Neuronpedia

    INDEX
    Explanations

    profile traits

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _One
    -0.07
    terrain
    -0.07
    ATTLE
    -0.06
     operations
    -0.06
    서는
    -0.06
    пов
    -0.06
    нила
    -0.06
    _literal
    -0.06
     Musical
    -0.06
    ického
    -0.06
    POSITIVE LOGITS
     �
    0.07
    км
    0.07
    �
    0.06
    ครบ
    0.06
    _Return
    0.06
     HEL
    0.06
    Gtk
    0.06
     Kafka
    0.06
     кожи
    0.06
     χα
    0.06
    Act Density 0.067%

    No Known Activations