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

    Neuronpedia

    INDEX
    Explanations

    speech

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     язы
    -0.07
     物
    -0.07
     Nobody
    -0.06
     체
    -0.06
    Blood
    -0.06
    猪
    -0.06
     bending
    -0.06
    哲
    -0.06
     Sche
    -0.06
     Yamaha
    -0.06
    POSITIVE LOGITS
    ter
    0.06
    "),
↵
    0.06
    VOKE
    0.06
    
    0.06
     investigación
    0.06
    ρι
    0.06
    Từ
    0.06
     bp
    0.06
    ∏
    0.06
    	priv
    0.06
    Act Density 0.010%

    No Known Activations