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

    Neuronpedia

    INDEX
    Explanations

    enabled javascript

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     configur
    -0.07
     interrupted
    -0.07
     Minute
    -0.07
     SWT
    -0.07
     surv
    -0.07
    ieg
    -0.06
     pus
    -0.06
    /conf
    -0.06
     veut
    -0.06
     Georg
    -0.06
    POSITIVE LOGITS
     scandals
    0.06
    럴
    0.06
     yardımcı
    0.06
     بش
    0.06
     dad
    0.06
     Johnny
    0.06
     Perm
    0.06
    Manchester
    0.06
     μέ
    0.06
    -shadow
    0.05
    Act Density 0.005%

    No Known Activations