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

    Neuronpedia

    INDEX
    Explanations

    networking/algorithms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    arn
    -0.08
    icial
    -0.08
    erders
    -0.08
     vieille
    -0.07
     wechsel
    -0.07
     Cosmic
    -0.07
     rise
    -0.07
    .modal
    -0.07
    oscopic
    -0.07
    osp
    -0.07
    POSITIVE LOGITS
     dispar
    0.08
     counsel
    0.08
     spat
    0.08
     информ
    0.08
     dispersed
    0.08
    คิดเห็น
    0.08
     letu
    0.07
    igens
    0.07
    Linejoin
    0.07
     informer
    0.07
    Act Density 0.001%

    No Known Activations