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

    Neuronpedia

    INDEX
    Explanations

    new followed by nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autres
    0.22
     primeiro
    0.21
    Modelo
    0.21
     recentes
    0.21
    Other
    0.21
    ish
    0.21
     Other
    0.20
    其他
    0.20
    Opened
    0.20
     střed
    0.20
    POSITIVE LOGITS
     layers
    0.30
     layer
    0.25
    クトル
    0.24
    维度
    0.24
    layers
    0.24
    层面
    0.23
     levels
    0.23
     LAYER
    0.23
     ಸುತ್ತ
    0.22
     Layers
    0.22
    Act Density 0.022%

    No Known Activations