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

    Neuronpedia

    INDEX
    Explanations

    Conditional/concessional statements

    np_max-act · gemini-2.0-flash

    The neuron is looking for numeric tokens—especially decimal or floating-point numbers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    などの
    -0.06
    _BUFF
    -0.06
    /_
    -0.06
     Kensington
    -0.06
     Özellikle
    -0.06
    　　 　 　 　
    -0.06
    　　　 　 　 　
    -0.06
    〇
    -0.06
     Beacon
    -0.06
     headset
    -0.05
    POSITIVE LOGITS
    (mm
    0.07
     roofs
    0.07
    xcc
    0.07
     слу
    0.07
     unofficial
    0.07
     emphas
    0.06
    (click
    0.06
     truncated
    0.06
     Smartphone
    0.06
     intimidate
    0.06
    Act Density 0.009%

    No Known Activations