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

    Neuronpedia

    INDEX
    Explanations

    speculation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Jahres
    -0.07
    _REGS
    -0.07
     Kup
    -0.06
    IED
    -0.06
    하지만
    -0.06
    费
    -0.06
     Kak
    -0.06
    eer
    -0.06
     their
    -0.06
     optimism
    -0.06
    POSITIVE LOGITS
    pun
    0.08
    (dummy
    0.07
     Nin
    0.06
     distorted
    0.06
    iswa
    0.06
     Connect
    0.06
     Coron
    0.06
     svc
    0.06
     thù
    0.06
     &=
    0.06
    Act Density 0.045%

    No Known Activations