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

    Neuronpedia

    INDEX
    Explanations

    technical/code text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     вывод
    -0.07
    lineEdit
    -0.07
     предпри
    -0.07
    fore
    -0.07
     sinister
    -0.07
     Forest
    -0.06
    ecessarily
    -0.06
    basket
    -0.06
    append
    -0.06
     forefront
    -0.06
    POSITIVE LOGITS
    ARATION
    0.07
     "<
    0.06
    ?;↵
    0.06
     Strawberry
    0.06
     ale
    0.06
     hes
    0.06
    Advice
    0.06
    :
    0.06
     Pony
    0.06
     Rath
    0.06
    Act Density 0.000%

    No Known Activations