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

    Neuronpedia

    INDEX
    Explanations

    beginning HTML tag

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    B
    0.65
     de
    0.63
    O
    0.61
    K
    0.59
    M
    0.55
    ↵
    0.55
    Cam
    0.55
    Coff
    0.55
    С
    0.54
    the
    0.54
    POSITIVE LOGITS
    WithFieldContext
    0.54
    შინ
    0.54
    incinnati
    0.54
     Miami
    0.51
     ライト
    0.51
     Sociology
    0.50
     DENUMIRE
    0.50
    HTTPSampler
    0.49
     nameWithOwner
    0.49
     ಬಿಜೆಪಿ
    0.49
    Act Density 0.000%

    No Known Activations