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

    Neuronpedia

    INDEX
    Explanations

    celebrating love

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     পুস্তক
    0.44
     marquées
    0.41
     لکھنے
    0.41
    itabbo
    0.39
     publicKey
    0.38
    ྗ
    0.38
    짖
    0.38
    不僅
    0.38
     لکھ
    0.37
     catheters
    0.37
    POSITIVE LOGITS
     krä
    0.38
     Ви
    0.38
     Negro
    0.38
    วิธี
    0.37
     minimalist
    0.36
     Opus
    0.36
    av
    0.36
     Diva
    0.36
    ór
    0.35
    keh
    0.35
    Act Density 0.000%

    No Known Activations