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

    Neuronpedia

    INDEX
    Explanations

    Snippets of text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Transformers
    -0.07
     TERMIN
    -0.06
     SU
    -0.06
    textView
    -0.06
    irit
    -0.06
    sled
    -0.06
     chast
    -0.06
    /de
    -0.06
    _MAY
    -0.06
    _se
    -0.06
    POSITIVE LOGITS
     αρ
    0.07
    bindParam
    0.07
    ?>/
    0.06
    	utils
    0.06
     natuur
    0.06
    بر
    0.06
    resize
    0.06
     이름
    0.06
    /setup
    0.06
    ()=>
    0.06
    Act Density 0.000%

    No Known Activations