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

    Neuronpedia

    INDEX
    Explanations

    Make context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ayana
    0.41
     Fung
    0.39
    變得
    0.39
     sprinkled
    0.36
     اتارنا
    0.35
    man
    0.34
    变得
    0.34
    AIS
    0.34
    ELDS
    0.33
    𝔦
    0.33
    POSITIVE LOGITS
    முகம்
    0.41
    큘
    0.40
    ное
    0.39
     pagos
    0.39
     MediaQuery
    0.39
     Hartley
    0.39
    譚
    0.38
     ineffective
    0.37
    खाली
    0.37
     seu
    0.37
    Act Density 0.000%

    No Known Activations