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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Appearance
    -0.07
    rese
    -0.07
    *i
    -0.06
    保護
    -0.06
    craft
    -0.06
    Mbps
    -0.06
    _POSITION
    -0.06
    �
    -0.06
     Ori
    -0.06
    世
    -0.06
    POSITIVE LOGITS
    ‐‐
    0.06
     Creative
    0.06
     objc
    0.06
    วม
    0.06
     있음
    0.06
     TODO
    0.06
     默认
    0.06
    _ATTRIBUTE
    0.06
     admin
    0.06
    ivar
    0.06
    Act Density 0.106%

    No Known Activations