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

    Neuronpedia

    INDEX
    Explanations

    assumes / implies that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Capsule
    0.39
    inati
    0.39
     remotely
    0.38
    mated
    0.38
    SERVATION
    0.37
     Reserva
    0.37
     л
    0.37
    Colon
    0.37
     गीता
    0.37
     മാത്ര
    0.37
    POSITIVE LOGITS
     plexus
    0.44
    謝
    0.42
     problemat
    0.41
    proble
    0.39
     boyhood
    0.39
     problemas
    0.38
     baseApiPath
    0.38
    pleasant
    0.37
    smiling
    0.37
     менедже
    0.37
    Act Density 0.001%

    No Known Activations