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

    Neuronpedia

    INDEX
    Explanations

    controller dialogue

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    \_
    0.80
     exhort
    0.80
     간단
    0.80
     Nearby
    0.79
    
    0.79
    \"]
    0.78
     FaceTime
    0.77
     Dispose
    0.77
    ността
    0.77
     Coachella
    0.76
    POSITIVE LOGITS
    pt
    0.85
    re
    0.75
    тит
    0.74
    τ
    0.74
    OUS
    0.73
    TAIN
    0.73
    pp
    0.71
    tail
    0.71
     park
    0.71
    อ
    0.71
    Act Density 0.000%

    No Known Activations