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

    Neuronpedia

    INDEX
    Explanations

    through

    np_max-act · gemini-2.0-flash

    The neuron primarily responds to occurrences of the word “through” (and its sub-token fragments).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     cors
    -0.07
     GtkWidget
    -0.07
     Ign
    -0.06
     trails
    -0.06
    -at
    -0.06
    tre
    -0.06
    .buffer
    -0.06
     inputFile
    -0.06
     between
    -0.06
     mist
    -0.06
    POSITIVE LOGITS
    ่ว
    0.07
     issu
    0.07
    セ
    0.07
    odesk
    0.07
     نتیجه
    0.06
    户
    0.06
    ий
    0.06
    méně
    0.06
    �
    0.06
    _REV
    0.06
    Act Density 0.015%

    No Known Activations