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

    Neuronpedia

    INDEX
    Explanations

    college

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    INDOW
    -0.07
     kou
    -0.07
    ══
    -0.07
    onor
    -0.06
     geb
    -0.06
     İs
    -0.06
     PS
    -0.06
    ์จ
    -0.06
     九
    -0.06
    ARRIER
    -0.06
    POSITIVE LOGITS
     Catalonia
    0.07
    학교
    0.07
    ılır
    0.07
    ").↵↵
    0.07
    �
    0.06
     insects
    0.06
    fun
    0.06
    _dec
    0.06
     *)((
    0.06
    もっと
    0.06
    Act Density 0.007%

    No Known Activations