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

    Neuronpedia

    INDEX
    Explanations

    research paper references

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    advance
    -0.07
    .Conv
    -0.07
    deriv
    -0.07
     slicing
    -0.07
    arto
    -0.07
    [cur
    -0.06
    (cam
    -0.06
    =this
    -0.06
    .Start
    -0.06
    -bordered
    -0.06
    POSITIVE LOGITS
     prowess
    0.08
     faker
    0.07
    脉
    0.07
    舆情
    0.07
    堋
    0.07
    솨
    0.06
    高低
    0.06
     NSLayoutConstraint
    0.06
     voyeur
    0.06
     Doom
    0.06
    Act Density 0.002%

    No Known Activations