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

    Neuronpedia

    INDEX
    Explanations

    side

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     PCM
    -0.08
    PLAIN
    -0.07
     Při
    -0.07
    اشت
    -0.07
     máy
    -0.07
    imei
    -0.06
    ashes
    -0.06
    	bit
    -0.06
    tej
    -0.06
    @m
    -0.06
    POSITIVE LOGITS
    .follow
    0.07
    端
    0.07
     thang
    0.07
     슬
    0.06
     �
    0.06
     queens
    0.06
    ****************************
    0.06
    安全
    0.06
     kills
    0.06
    细胞
    0.06
    Act Density 0.008%

    No Known Activations