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

    Neuronpedia

    INDEX
    Explanations

    many

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on the quantifier “many,” marking occurrences of that word in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    otomy
    -0.07
     вд
    -0.07
    отреб
    -0.07
     sand
    -0.06
     Sand
    -0.06
    دری
    -0.06
    �
    -0.06
     sauce
    -0.06
     serious
    -0.06
    NORMAL
    -0.06
    POSITIVE LOGITS
    $l
    0.07
    zoek
    0.07
    S
    0.07
     applicationWill
    0.07
    s
    0.07
    Most
    0.07
     getLast
    0.06
    gL
    0.06
    nek
    0.06
    .MoveNext
    0.06
    Act Density 0.039%

    No Known Activations