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

    Neuronpedia

    INDEX
    Explanations

    authors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hancock
    -0.07
    映
    -0.07
    ('{}
    -0.06
     Hyde
    -0.06
     саме
    -0.06
    宅
    -0.06
    
    -0.06
    �
    -0.06
    ช
    -0.06
     pie
    -0.06
    POSITIVE LOGITS
    _proba
    0.07
     vez
    0.06
     هم
    0.06
     alarm
    0.06
     RTVF
    0.06
     emphasizing
    0.06
     chiế
    0.06
    attend
    0.06
    Af
    0.06
    /backend
    0.06
    Act Density 0.001%

    No Known Activations