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

    Neuronpedia

    INDEX
    Explanations

    row

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Buddh
    -0.07
     여러분
    -0.07
     Cuộc
    -0.07
    ᵀ
    -0.07
    ὕ
    -0.07
    귿
    -0.06
    ıldı
    -0.06
    聚合
    -0.06
     czł
    -0.06
    獍
    -0.06
    POSITIVE LOGITS
     sélection
    0.08
              
↵
    0.08
     stainless
    0.07
     calle
    0.07
     bathroom
    0.07
     sacks
    0.07
    𬬹
    0.07
     pooled
    0.07
    -sponsored
    0.07
     worrying
    0.07
    Act Density 0.008%

    No Known Activations