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

    Neuronpedia

    INDEX
    Explanations

    Hor

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Encoding
    -0.07
    �
    -0.06
    	If
    -0.06
    BX
    -0.06
     rij
    -0.06
     přímo
    -0.06
    signal
    -0.06
     MESSAGE
    -0.06
    _HI
    -0.06
    _take
    -0.05
    POSITIVE LOGITS
    urm
    0.07
     제출
    0.07
     Dungeons
    0.07
     Markets
    0.07
    ーフ
    0.07
     Down
    0.06
    stanov
    0.06
     Deutsch
    0.06
     цих
    0.06
     Clara
    0.06
    Act Density 0.092%

    No Known Activations