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

    Neuronpedia

    INDEX
    Explanations

    phenomenon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     imprisonment
    -0.07
     हव
    -0.07
     classifiers
    -0.06
     Claire
    -0.06
    =log
    -0.06
     Gordon
    -0.06
     сигн
    -0.06
     Epstein
    -0.06
    >R
    -0.06
    ٨
    -0.06
    POSITIVE LOGITS
     ακό
    0.06
     MutableLiveData
    0.06
    rippling
    0.06
     bás
    0.06
    _exit
    0.06
     --↵↵
    0.06
    .refs
    0.06
     أكبر
    0.06
     центра
    0.06
     ripple
    0.06
    Act Density 0.061%

    No Known Activations