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

    Neuronpedia

    INDEX
    Explanations

    expressing willingness to engage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     movie
    0.49
     de
    0.48
     glad
    0.48
     joker
    0.47
     con
    0.46
     sofern
    0.46
     Nielsen
    0.46
     van
    0.46
     wise
    0.46
     Weber
    0.46
    POSITIVE LOGITS
    ಂಗ್ರೆ
    0.51
     breakouts
    0.49
    蔻
    0.48
    近平
    0.46
     খুঁ
    0.46
    মতী
    0.46
    ↯
    0.46
    titles
    0.45
    toBytes
    0.45
    myLabels
    0.45
    Act Density 0.002%

    No Known Activations