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

    Neuronpedia

    INDEX
    Explanations

    ab

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bài
    -0.07
    ريح
    -0.07
    _ve
    -0.07
     Basics
    -0.07
    념
    -0.07
     ha
    -0.07
    _MUX
    -0.07
    	that
    -0.07
    _sa
    -0.07
    _fence
    -0.06
    POSITIVE LOGITS
    �
    0.08
     bonding
    0.08
    文娱
    0.07
     Hogwarts
    0.07
     spending
    0.07
    土豆
    0.07
    CGColor
    0.06
    (power
    0.06
    '],$
    0.06
     depreci
    0.06
    Act Density 0.002%

    No Known Activations