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

    Neuronpedia

    INDEX
    Explanations

    legal writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     RTS
    -0.07
    разу
    -0.07
     fronts
    -0.06
     Installation
    -0.06
    YLE
    -0.06
     "[
    -0.06
    ouflage
    -0.06
     fw
    -0.06
     TRUE
    -0.06
     rs
    -0.06
    POSITIVE LOGITS
    OTOS
    0.07
     лок
    0.07
    .Apis
    0.07
    isser
    0.06
    errals
    0.06
     Burlington
    0.06
     음악
    0.06
    の
    0.06
     laden
    0.06
    .END
    0.06
    Act Density 0.006%

    No Known Activations