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

    Neuronpedia

    INDEX
    Explanations

    not

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Philips
    -0.06
    esel
    -0.06
    ỹ
    -0.06
     discrimination
    -0.06
    getState
    -0.05
     Adelaide
    -0.05
    обходим
    -0.05
    _PAD
    -0.05
     Optimization
    -0.05
    anko
    -0.05
    POSITIVE LOGITS
     lenses
    0.08
     aquel
    0.07
     sweaty
    0.07
     BASIC
    0.07
     cub
    0.06
    _WINDOWS
    0.06
    _ASM
    0.06
    MISSION
    0.06
     dbs
    0.06
    cxx
    0.06
    Act Density 0.001%

    No Known Activations