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

    Neuronpedia

    INDEX
    Explanations

    general purpose descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     asympt
    0.39
    Miss
    0.37
    php
    0.35
    Multiple
    0.35
    greet
    0.35
    LCM
    0.35
    Ind
    0.35
    Weight
    0.34
    Planck
    0.34
    Sept
    0.34
    POSITIVE LOGITS
     Poc
    0.42
     integrator
    0.41
    ataires
    0.40
     သင်
    0.40
     escolher
    0.40
    responseData
    0.40
     terminar
    0.39
     trasc
    0.39
     direcion
    0.39
     මිල
    0.38
    Act Density 0.000%

    No Known Activations