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

    Neuronpedia

    INDEX
    Explanations

    Build Certificate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    alto
    0.44
    oncesto
    0.42
    දු
    0.41
    ान्त
    0.39
     진
    0.38
    iénd
    0.38
     различных
    0.38
     पत्थर
    0.38
    虧
    0.38
    listof
    0.38
    POSITIVE LOGITS
     Pupp
    0.46
     Benutz
    0.43
    Manus
    0.42
    갬
    0.42
     Booking
    0.42
     grunds
    0.42
     steric
    0.42
     munk
    0.41
     Completely
    0.41
    NOP
    0.40
    Act Density 0.000%

    No Known Activations