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

    Neuronpedia

    INDEX
    Explanations

    201

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Adapt
    -0.07
     Vegas
    -0.06
    	current
    -0.06
    ～
    -0.06
     út
    -0.06
    ograd
    -0.06
     similarities
    -0.06
    [text
    -0.06
    (that
    -0.06
    (shell
    -0.06
    POSITIVE LOGITS
    517
    0.07
     cif
    0.07
    سانی
    0.06
    UserId
    0.06
     문자
    0.06
     المف
    0.06
    57
    0.06
    080
    0.06
    magic
    0.06
    ￣
    0.06
    Act Density 0.004%

    No Known Activations