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

    Neuronpedia

    INDEX
    Explanations

    ambiguous code/method calls

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
     municipalities
    -0.06
     부탁
    -0.06
    ουργ
    -0.06
     hôm
    -0.06
     싸
    -0.06
     MIC
    -0.06
     суп
    -0.06
    %'↵
    -0.06
    นาม
    -0.05
    POSITIVE LOGITS
    (high
    0.08
    flip
    0.07
     picking
    0.07
    =all
    0.07
    .FirstName
    0.07
    uintptr
    0.07
    第一
    0.06
    나는
    0.06
     Rain
    0.06
    LOSE
    0.06
    Act Density 0.008%

    No Known Activations