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

    Neuronpedia

    INDEX
    Explanations

    code characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dominates
    -0.07
    mm
    -0.07
    Neither
    -0.07
    Released
    -0.07
     nod
    -0.07
    ,num
    -0.06
    ；↵
    -0.06
    ुन
    -0.06
    arently
    -0.06
    ublished
    -0.06
    POSITIVE LOGITS
     Acer
    0.07
     alteration
    0.06
     Paste
    0.06
     탈
    0.06
     insist
    0.06
     Cobra
    0.06
     tě
    0.06
    няют
    0.06
     last
    0.06
    çesi
    0.06
    Act Density 0.026%

    No Known Activations