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

    Neuronpedia

    INDEX
    Explanations

    unexpected

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     flats
    -0.07
     Tiger
    -0.07
    :^{↵
    -0.06
    .VERTICAL
    -0.06
    -body
    -0.06
     chanting
    -0.06
     split
    -0.06
     Ther
    -0.06
     jose
    -0.06
    .Atoi
    -0.06
    POSITIVE LOGITS
     unexpected
    0.14
     Unexpected
    0.10
    Unexpected
    0.10
     unexpectedly
    0.09
    unexpected
    0.09
     unfore
    0.08
    atchet
    0.07
    ок
    0.07
     �
    0.07
     husus
    0.06
    Act Density 0.008%

    No Known Activations