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

    Neuronpedia

    INDEX
    Explanations

    claim6for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tark
    0.89
     incrementar
    0.89
    िवार
    0.88
    oliko
    0.88
    tki
    0.88
    uigen
    0.88
     Watan
    0.86
    *{-
    0.86
    ди
    0.86
    uidos
    0.86
    POSITIVE LOGITS
     Congratulations
    0.95
     Play
    0.91
     Communicate
    0.91
     Postgraduate
    0.89
     Hans
    0.88
     Learn
    0.87
     Verónica
    0.86
    А
    0.86
     Provide
    0.86
     Lech
    0.86
    Act Density 0.000%

    No Known Activations