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

    Neuronpedia

    INDEX
    Explanations

    get the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ꮎ
    0.46
    斓
    0.46
    菉
    0.43
     mustn
    0.41
    arenko
    0.40
    捩
    0.40
    essional
    0.40
    oción
    0.39
    ўнай
    0.39
    difficult
    0.39
    POSITIVE LOGITS
    icules
    0.38
     والله
    0.36
     LIABLE
    0.35
     blood
    0.34
    TAT
    0.34
    卟
    0.34
    قط
    0.34
    ards
    0.33
    forge
    0.33
    ylabel
    0.33
    Act Density 0.000%

    No Known Activations