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

    Neuronpedia

    INDEX
    Explanations

    constant

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    \modules
    -0.06
    ladığ
    -0.06
     Ú
    -0.06
     теор
    -0.06
    ????????????????
    -0.06
    Element
    -0.06
     身
    -0.06
    front
    -0.06
     tidal
    -0.06
     jumped
    -0.06
    POSITIVE LOGITS
    leen
    0.07
    ICK
    0.06
    (acc
    0.06
     marginal
    0.06
    pegawai
    0.06
     nicely
    0.06
    .builder
    0.06
     وال
    0.06
     něm
    0.06
    assen
    0.06
    Act Density 0.000%

    No Known Activations