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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     suffice
    -0.07
     ===>
    -0.07
    ناق
    -0.07
     aunque
    -0.07
    ancial
    -0.07
     Türk
    -0.07
     liberals
    -0.06
     holland
    -0.06
    统筹推进
    -0.06
     unto
    -0.06
    POSITIVE LOGITS
    推广
    0.07
     Same
    0.07
    𝗘
    0.07
    (point
    0.07
    _person
    0.07
    Frames
    0.06
    _markers
    0.06
     Sole
    0.06
    Images
    0.06
     Said
    0.06
    Act Density 0.002%

    No Known Activations