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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    The neuron consistently lights up on isolated decimal‐number fragments (floating-point literals) rather than ordinary words.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     methyl
    -0.06
    .inv
    -0.06
     consortium
    -0.06
     NIL
    -0.06
    函
    -0.06
    �
    -0.06
    iesel
    -0.06
     startPosition
    -0.06
    zu
    -0.06
    標準
    -0.06
    POSITIVE LOGITS
    ,V
    0.07
     pokemon
    0.06
    >-
    0.06
    แข
    0.06
    ricanes
    0.06
    $smarty
    0.06
    =L
    0.06
     f
    0.06
     Vec
    0.06
     sharply
    0.06
    Act Density 0.095%

    No Known Activations