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

    Neuronpedia

    INDEX
    Explanations

    actions or descriptions followed by details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Widers
    0.42
     fein
    0.41
    Low
    0.40
     వె
    0.40
    韦
    0.40
     ತಿಳಿದ
    0.40
    眉头
    0.39
     Tempt
    0.39
     décro
    0.39
     reed
    0.38
    POSITIVE LOGITS
    ㅃ
    0.50
    ബോ
    0.49
     negativos
    0.49
     segmento
    0.47
     uso
    0.47
    imgur
    0.47
    podob
    0.47
    andır
    0.46
     vua
    0.46
    키
    0.45
    Act Density 0.000%

    No Known Activations