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

    Neuronpedia

    INDEX
    Explanations

    list indexing, counting, Python

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ewell
    0.39
    ethylamine
    0.38
    getPrototypeOf
    0.38
    rza
    0.38
    emann
    0.37
    Committee
    0.37
    endente
    0.37
    adap
    0.36
    emun
    0.36
    ęż
    0.36
    POSITIVE LOGITS
     digits
    0.42
     digitization
    0.39
    อีก
    0.38
     digital
    0.37
     breeze
    0.37
    仿佛
    0.36
     Mét
    0.36
     slashed
    0.36
     Python
    0.35
     digitalization
    0.35
    Act Density 0.002%

    No Known Activations