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

    Neuronpedia

    INDEX
    Explanations

    drip

    np_max-act · gemini-2.0-flash

    The neuron responds to onomatopoetic “drip”-type tokens—that is, words evoking dripping or liquid-droplet sounds.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     mat
    -0.06
    -den
    -0.06
     Freund
    -0.06
     mascul
    -0.06
    .LoadScene
    -0.06
    .box
    -0.06
    发生
    -0.06
     promotes
    -0.06
     تجاری
    -0.06
    _modes
    -0.06
    POSITIVE LOGITS
     dripping
    0.13
     dri
    0.10
     drip
    0.10
    django
    0.07
    quito
    0.07
    .Bit
    0.07
     SDK
    0.07
    loe
    0.07
    etti
    0.07
     TOP
    0.07
    Act Density 0.003%

    No Known Activations