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

    Neuronpedia

    INDEX
    Explanations

    but/still (didn't work)

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.07
    Airport
    -0.07
    更新
    -0.06
    	Debug
    -0.06
    ativas
    -0.06
     unst
    -0.06
    μένη
    -0.06
    ラ
    -0.06
    ativo
    -0.06
    ativa
    -0.06
    POSITIVE LOGITS
     peace
    0.07
     march
    0.07
     superb
    0.06
     البي
    0.06
     awe
    0.06
    .add
    0.06
     bats
    0.06
     caption
    0.06
    erculosis
    0.06
     fabulous
    0.06
    Act Density 0.055%

    No Known Activations