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

    Neuronpedia

    INDEX
    Explanations

    Punctuation/common words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     felon
    -0.07
     accepting
    -0.07
     gol
    -0.06
    ción
    -0.06
     spawns
    -0.06
     принцип
    -0.06
    definition
    -0.06
    _modifier
    -0.06
    :^{↵
    -0.06
    PostalCodesNL
    -0.06
    POSITIVE LOGITS
    Smith
    0.07
    	then
    0.07
    UARIO
    0.06
     Garlic
    0.06
    .skills
    0.06
     Diesel
    0.06
    	strcpy
    0.06
    Projects
    0.06
    )=(
    0.06
    ับการ
    0.06
    Act Density 0.000%

    No Known Activations