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

    Neuronpedia

    INDEX
    Explanations

    inline

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     heed
    -0.06
    ề
    -0.06
     advent
    -0.06
     tol
    -0.06
     Nikol
    -0.06
    _am
    -0.06
    FAIL
    -0.06
     exhaust
    -0.05
    409
    -0.05
     mans
    -0.05
    POSITIVE LOGITS
     tout
    0.07
    _BB
    0.07
     아주
    0.07
    langs
    0.07
     horizontally
    0.06
    /ayushman
    0.06
    Configure
    0.06
     Holdings
    0.06
    SGlobal
    0.06
     backgrounds
    0.06
    Act Density 0.001%

    No Known Activations