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

    Neuronpedia

    INDEX
    Explanations

    informational purposes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bob
    0.41
     Academy
    0.39
     Bob
    0.39
     porro
    0.39
    salon
    0.38
    academy
    0.38
     Salon
    0.38
    oresis
    0.38
    bob
    0.37
    Salon
    0.37
    POSITIVE LOGITS
    Cin
    0.39
     চৈত
    0.39
     பிறந்த
    0.38
     Khr
    0.36
    তাহাদের
    0.36
     ciné
    0.35
     computeEncoder
    0.35
     Shred
    0.35
    FO
    0.35
     crist
    0.35
    Act Density 0.009%

    No Known Activations