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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     EDM
    -0.06
    اره
    -0.06
    apro
    -0.06
    俺
    -0.06
     Sri
    -0.06
    ाहक
    -0.06
     tes
    -0.06
     Santana
    -0.06
    ipers
    -0.06
     eens
    -0.06
    POSITIVE LOGITS
    .uc
    0.07
    isActive
    0.07
    支援
    0.07
    removeClass
    0.06
    ปฏ
    0.06
    	errors
    0.06
    	Console
    0.06
    .obtain
    0.06
    ([])↵
    0.06
    liced
    0.06
    Act Density 0.000%

    No Known Activations