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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     limbs
    -0.07
     CONTEXT
    -0.07
    анг
    -0.07
     bilim
    -0.06
    _ATTR
    -0.06
     screw
    -0.06
    ~-~-~-~-
    -0.06
     euth
    -0.06
     Cmd
    -0.06
    PASSWORD
    -0.06
    POSITIVE LOGITS
    /init
    0.07
    olls
    0.07
     recommending
    0.06
    Dt
    0.06
    >,</
    0.06
     میشود
    0.06
    _Store
    0.06
    andon
    0.06
    employed
    0.06
     quot
    0.06
    Act Density 0.006%

    No Known Activations