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

    Neuronpedia

    INDEX
    Explanations

    Formatting prompts with newlines

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .parts
    -0.08
     dispatched
    -0.08
     জানিয়
    -0.07
     wrath
    -0.07
     семей
    -0.07
     aeg
    -0.07
     জানতে
    -0.07
    興
    -0.07
     verborgen
    -0.07
     flaw
    -0.07
    POSITIVE LOGITS
     Outro
    0.07
     Forms
    0.07
    /tr
    0.07
     Bid
    0.07
    _bid
    0.07
     forms
    0.07
    hos
    0.07
    osed
    0.07
    uil
    0.07
     outro
    0.07
    Act Density 0.001%

    No Known Activations