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

    Neuronpedia

    INDEX
    Explanations

    ase

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.07
    _CHOICES
    -0.07
    灭
    -0.07
     trời
    -0.06
    cu
    -0.06
    對
    -0.06
    chat
    -0.06
    MT
    -0.06
     MST
    -0.06
    PP
    -0.06
    POSITIVE LOGITS
     nguyên
    0.07
     strategy
    0.06
    .hidden
    0.06
    -more
    0.06
     Mondays
    0.06
     pública
    0.06
     внимание
    0.06
     marketing
    0.06
     irritating
    0.06
    Dave
    0.06
    Act Density 0.002%

    No Known Activations