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

    Neuronpedia

    INDEX
    Explanations

    mean

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     finds
    -0.07
     certains
    -0.07
    uly
    -0.06
    _COLS
    -0.06
     soc
    -0.06
     sexually
    -0.06
     mun
    -0.06
    ataire
    -0.06
     Charity
    -0.06
    _none
    -0.06
    POSITIVE LOGITS
    remark
    0.07
    MemoryWarning
    0.06
    (INT
    0.06
    혜
    0.06
    (parseInt
    0.06
     cinnamon
    0.06
    -equ
    0.06
    όν
    0.06
    /operators
    0.06
    ┬
    0.06
    Act Density 0.004%

    No Known Activations