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

    Neuronpedia

    INDEX
    Explanations

    Markdown tokens

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (layout
    -0.07
     stretching
    -0.06
    Expand
    -0.06
    cü
    -0.06
     pictured
    -0.06
     cbo
    -0.06
     expelled
    -0.06
     hned
    -0.06
    Makes
    -0.06
     toasted
    -0.06
    POSITIVE LOGITS
     Ра
    0.07
    perm
    0.07
    ическим
    0.07
    .getResponse
    0.07
    enerative
    0.06
    ılığ
    0.06
     остан
    0.06
    .getNode
    0.06
     опер
    0.06
     необходим
    0.06
    Act Density 0.001%

    No Known Activations