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

    Neuronpedia

    INDEX
    Explanations

    code/regex

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tying
    -0.08
    '))->
    -0.07
    ..........
    -0.07
    tober
    -0.07
    As
    -0.07
    Dean
    -0.07
    ил
    -0.07
    事宜
    -0.06
    荁
    -0.06
     necessity
    -0.06
    POSITIVE LOGITS
    ()?;↵
    0.08
    -wing
    0.08
    ({});↵
    0.07
     archive
    0.07
    :";↵
    0.07
    wort
    0.07
    >());↵↵
    0.07
    skin
    0.07
    -hide
    0.07
     cc
    0.07
    Act Density 0.007%

    No Known Activations