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

    Neuronpedia

    INDEX
    Explanations

    code try except

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     warnings
    0.72
     CSC
    0.71
    osit
    0.70
    Dowell
    0.70
    inales
    0.69
     stop
    0.68
    geke
    0.68
    alid
    0.67
    NaOMe
    0.66
    停車
    0.66
    POSITIVE LOGITS
     surround
    0.90
     Surround
    0.84
     surrounds
    0.79
     Env
    0.79
     surrounding
    0.78
    try
    0.74
     surrounded
    0.72
     attorno
    0.68
     wrapped
    0.68
     Fletcher
    0.68
    Act Density 0.051%

    No Known Activations