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

    Neuronpedia

    INDEX
    Explanations

    read

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     prediction
    -0.07
     předpok
    -0.07
    RB
    -0.06
    ihil
    -0.06
     predictions
    -0.06
    JNIEXPORT
    -0.06
    olation
    -0.06
     winners
    -0.06
    čný
    -0.06
    ارد
    -0.06
    POSITIVE LOGITS
     mindfulness
    0.07
     URLSession
    0.07
     tram
    0.07
     Wrath
    0.06
     occured
    0.06
    coder
    0.06
    _eq
    0.06
    .once
    0.06
    可以
    0.06
     Ex
    0.06
    Act Density 0.003%

    No Known Activations