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

    Neuronpedia

    INDEX
    Explanations

    sphere calculations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ker
    -0.09
     Proposition
    -0.09
     opposition
    -0.09
    拜
    -0.08
    _FN
    -0.08
    Bez
    -0.08
     Lex
    -0.07
     �
    -0.07
     proposition
    -0.07
    黑人
    -0.07
    POSITIVE LOGITS
     heights
    0.10
     altura
    0.09
    -height
    0.09
     height
    0.09
    (height
    0.09
    	height
    0.09
    高さ
    0.08
     Height
    0.08
    .Height
    0.08
     displaced
    0.08
    Act Density 0.048%

    No Known Activations