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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _radius
    -0.06
     mansion
    -0.06
    vection
    -0.06
    _STATS
    -0.06
     inputStream
    -0.06
    OTT
    -0.06
     rb
    -0.06
     whats
    -0.06
    _invalid
    -0.06
    vos
    -0.06
    POSITIVE LOGITS
    арів
    0.08
    ются
    0.07
     edits
    0.07
     withhold
    0.07
    ,,,,
    0.07
    nocení
    0.07
     consumers
    0.06
    rollment
    0.06
     accred
    0.06
     предел
    0.06
    Act Density 0.000%

    No Known Activations