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

    Neuronpedia

    INDEX
    Explanations

    `and` followed by `*`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ય
    0.82
    ти
    0.82
    aaaa
    0.79
    aaa
    0.79
    annya
    0.75
    ד
    0.75
    aa
    0.74
    дах
    0.74
    很
    0.74
    कांच्या
    0.73
    POSITIVE LOGITS
     Recuer
    0.88
    습니다
    0.87
     afirma
    0.85
     Caleb
    0.85
     alrededor
    0.83
     ofrece
    0.82
     gql
    0.81
     Осо
    0.80
     велико
    0.79
     Vibr
    0.79
    Act Density 0.000%

    No Known Activations