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

    Neuronpedia

    INDEX
    Explanations

    faucet, start

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Sentencing
    0.46
     lyrics
    0.46
     fucking
    0.44
     declaratory
    0.44
     menikmati
    0.44
     sedang
    0.44
     sentencing
    0.44
     isomers
    0.43
     geçir
    0.42
     headquartered
    0.42
    POSITIVE LOGITS
    وزه
    0.47
    ificación
    0.42
    LoopBlend
    0.42
    ना
    0.42
    you
    0.41
    sel
    0.40
    fier
    0.40
    andin
    0.40
    uidado
    0.40
     Você
    0.39
    Act Density 0.006%

    No Known Activations