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

    Neuronpedia

    INDEX
    Explanations

    movement, direction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     highways
    -0.06
     Forever
    -0.06
     Gaut
    -0.06
     좋은
    -0.06
    محمد
    -0.06
    phies
    -0.06
     Peanut
    -0.06
    嗯
    -0.06
    \Exceptions
    -0.06
     Philosoph
    -0.06
    POSITIVE LOGITS
     listen
    0.08
     �
    0.07
    fh
    0.06
     img
    0.06
    percent
    0.06
     qty
    0.06
    �
    0.06
     italia
    0.06
    聚
    0.06
     existe
    0.06
    Act Density 0.028%

    No Known Activations