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

    Neuronpedia

    INDEX
    Explanations

    error logs

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric tokens—especially decimal numbers and timestamps—highlighting floating-point values in log output.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    asket
    -0.06
    Quiet
    -0.06
    кої
    -0.06
    						
↵
    -0.06
    mach
    -0.06
    _DIP
    -0.06
    ної
    -0.06
    Роз
    -0.05
    ForEach
    -0.05
     HALF
    -0.05
    POSITIVE LOGITS
     scp
    0.07
     $_
    0.07
     Productions
    0.07
    -с
    0.07
     법
    0.06
     slight
    0.06
     Yayın
    0.06
    าจารย
    0.06
    kp
    0.06
    قال
    0.06
    Act Density 0.001%

    No Known Activations