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

    Neuronpedia

    INDEX
    Explanations

    reflections

    np_max-act · gemini-2.0-flash

    This neuron detects floating‐point numeric tokens (decimal measurement values).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    �a
    -0.06
    /show
    -0.06
     hvě
    -0.06
     subdivision
    -0.06
     ува
    -0.06
    cete
    -0.06
     bisher
    -0.06
    >false
    -0.06
     ubytování
    -0.06
    655
    -0.06
    POSITIVE LOGITS
    masked
    0.08
    Right
    0.07
    at
    0.07
    ../../
    0.07
    	Created
    0.07
     principle
    0.07
    Memory
    0.07
     bitcoin
    0.07
    thrown
    0.06
    ату
    0.06
    Act Density 0.000%

    No Known Activations