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

    Neuronpedia

    INDEX
    Explanations

    functions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     zot
    -0.09
     अर्ज
    -0.08
     MLS
    -0.08
     संग
    -0.08
     MCC
    -0.07
     Meta
    -0.07
    াত্রী
    -0.07
     accompanied
    -0.07
     dozen
    -0.07
     umi
    -0.07
    POSITIVE LOGITS
     Ś
    0.08
    %%↵
    0.07
     Myself
    0.07
    Trou
    0.07
     miej
    0.07
     negativa
    0.07
    .Contract
    0.07
     Übersicht
    0.07
    рун
    0.07
     stationary
    0.07
    Act Density 0.003%

    No Known Activations