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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act · gemini-2.0-flash

    The neuron activates on floating-point numeric literals (decimal constants) in code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     undefeated
    -0.08
     Pik
    -0.06
     مح
    -0.06
     Legislature
    -0.06
    -te
    -0.06
    ichael
    -0.06
    vp
    -0.06
    迷
    -0.06
     phiếu
    -0.06
    घ
    -0.06
    POSITIVE LOGITS
     Fashion
    0.07
    .connect
    0.07
     �
    0.07
     =$
    0.06
     borders
    0.06
    "]="
    0.06
     getir
    0.06
     }↵↵↵↵↵↵
    0.06
     Carmen
    0.06
    .TR
    0.06
    Act Density 0.013%

    No Known Activations