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

    Neuronpedia

    INDEX
    Explanations

    clothing materials

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    =?
    -0.08
    &uuml
    -0.07
    _social
    -0.07
     Dyn
    -0.07
     Darwin
    -0.07
    ；
    -0.07
    รวจ
    -0.06
    .Save
    -0.06
     Projekt
    -0.06
     equipo
    -0.06
    POSITIVE LOGITS
    ोई
    0.07
    ализации
    0.06
    (gca
    0.06
    enedor
    0.06
    lığın
    0.06
    _iteration
    0.06
     천
    0.06
     prostě
    0.06
     đàn
    0.06
     lesbische
    0.06
    Act Density 0.009%

    No Known Activations