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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sugger
    -0.09
    agenda
    -0.08
    к
    -0.08
    diagram
    -0.08
     деген
    -0.08
    Maria
    -0.08
     seminar
    -0.08
    suggest
    -0.08
    inosaur
    -0.08
    ումը
    -0.08
    POSITIVE LOGITS
     additional
    0.09
     constraints
    0.09
     अतिरिक्त
    0.08
    Constraints
    0.08
     Additional
    0.08
     sizes
    0.08
     eras
    0.08
     fixed
    0.08
     exclusions
    0.07
     separators
    0.07
    Act Density 0.056%

    No Known Activations