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

    Neuronpedia

    INDEX
    Explanations

    stop words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     america
    -0.07
    먹
    -0.06
     보면
    -0.06
    ิด
    -0.06
     tamanho
    -0.06
     През
    -0.06
     courtroom
    -0.06
    χη
    -0.06
     день
    -0.06
    _children
    -0.06
    POSITIVE LOGITS
    _BUF
    0.07
    	resp
    0.06
    .val
    0.06
     anyway
    0.06
     gist
    0.06
    .Encode
    0.06
    だった
    0.06
    .abort
    0.06
    	SDL
    0.06
     معلومات
    0.06
    Act Density 0.000%

    No Known Activations