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

    Neuronpedia

    INDEX
    Explanations

    terms related to scientific or technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code comments and licenses

    np_acts-logits-general · gemini-2.0-flash

    self-employment tax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rillos
    -0.42
     chủ
    -0.40
    phens
    -0.37
     nhất
    -0.37
    حياتها
    -0.37
    łby
    -0.37
    keen
    -0.37
    эй
    -0.36
     ado
    -0.36
    ęż
    -0.35
    POSITIVE LOGITS
     *
    1.43
    (*
    1.31
    *
    1.27
     (*
    1.18
    =*
    1.12
    ,*
    1.06
     $*$
    1.04
     *_
    1.01
     ((*
    0.98
     $*
    0.97
    Act Density 0.323%

    No Known Activations