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

    Neuronpedia

    INDEX
    Explanations

    corrections clarifications admissions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     FALL
    -0.06
    سط
    -0.06
     Sorting
    -0.06
     Might
    -0.06
     výj
    -0.06
     setUp
    -0.06
     силь
    -0.06
    庆
    -0.06
     Ple
    -0.06
    win
    -0.06
    POSITIVE LOGITS
    _↵
    0.07
    _DT
    0.07
    .minLength
    0.07
     sexes
    0.07
    !
↵
    0.07
    ↵
    0.07
     $
↵
    0.06
    _hat
    0.06
    (jLabel
    0.06
    **↵
    0.06
    Act Density 0.002%

    No Known Activations