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

    Neuronpedia

    INDEX
    Explanations

    scientific experiments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	ON
    -0.07
    гу
    -0.07
    signup
    -0.07
     PLUS
    -0.07
    izin
    -0.07
    /reset
    -0.06
     demons
    -0.06
    (bean
    -0.06
     loosen
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     ACE
    0.08
    аниц
    0.07
     využití
    0.07
     použití
    0.06
    Georgia
    0.06
    ioneer
    0.06
    Administration
    0.06
     Pokud
    0.06
    _frac
    0.06
    五月
    0.06
    Act Density 0.048%

    No Known Activations