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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    draft
    -0.06
    wahl
    -0.06
    ิงหาคม
    -0.06
    _study
    -0.06
    =L
    -0.06
     イ
    -0.05
    ？”↵↵
    -0.05
    ＼＼
    -0.05
    ็จพระ
    -0.05
    PH
    -0.05
    POSITIVE LOGITS
    (rank
    0.07
    -mobile
    0.07
    testimonial
    0.07
    /resource
    0.06
    igu
    0.06
    -analytics
    0.06
    ichage
    0.06
     distressed
    0.06
     Ancient
    0.06
     screenSize
    0.06
    Act Density 0.048%

    No Known Activations