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

    Neuronpedia

    INDEX
    Explanations

    Code/configuration files

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     beforehand
    -0.07
     LX
    -0.07
    شمالی
    -0.07
    UserRole
    -0.07
    FORM
    -0.06
    LIST
    -0.06
    php
    -0.06
     نیز
    -0.06
     درست
    -0.06
     preceded
    -0.06
    POSITIVE LOGITS
    prü
    0.06
    _MODIFIED
    0.06
     Silence
    0.06
    Lake
    0.06
    lag
    0.06
     खतर
    0.05
    waters
    0.05
    ][_
    0.05
     trest
    0.05
     ситуа
    0.05
    Act Density 0.169%

    No Known Activations