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

    Neuronpedia

    INDEX
    Explanations

    legal opinions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tablets
    -0.07
    _df
    -0.06
    okay
    -0.06
     kim
    -0.06
    loating
    -0.06
    _td
    -0.06
     affection
    -0.06
     Pressure
    -0.06
     sha
    -0.06
    _hom
    -0.06
    POSITIVE LOGITS
    ________________________________________________________________
    0.09
     Hiro
    0.08
    吨
    0.07
     Aren
    0.07
    ________________________________
    0.07
     Brave
    0.07
                                    
    0.06
    یزات
    0.06
    ritional
    0.06
     Fuß
    0.06
    Act Density 0.001%

    No Known Activations