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

    Neuronpedia

    INDEX
    Explanations

    ig

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    PopMatrix
    -0.07
    -On
    -0.07
     boundary
    -0.07
     water
    -0.07
     outer
    -0.07
     remembers
    -0.06
     pressure
    -0.06
    chemical
    -0.06
    .watch
    -0.06
     文件
    -0.06
    POSITIVE LOGITS
     Gig
    0.19
     gig
    0.18
     gigs
    0.13
     Ib
    0.07
    aysia
    0.06
    315
    0.06
    igung
    0.06
     Civic
    0.06
    敌
    0.06
     Priv
    0.06
    Act Density 0.002%

    No Known Activations