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

    Neuronpedia

    INDEX
    Explanations

    cancel

    np_max-act · gemini-2.0-flash

    The neuron highlights mentions of cancellation (e.g. “Cancellation,” “cancel,” “cancellations”) in booking or payment policies.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _requested
    -0.06
    柱
    -0.06
    trs
    -0.06
    ёт
    -0.06
    Her
    -0.06
    withErrors
    -0.06
     buy
    -0.06
    算
    -0.06
     XP
    -0.06
     Framework
    -0.06
    POSITIVE LOGITS
    blend
    0.07
     emerges
    0.07
    .Stderr
    0.07
    ofire
    0.07
     zajím
    0.06
    lei
    0.06
     besar
    0.06
    (Container
    0.06
    <Model
    0.06
    áš
    0.06
    Act Density 0.005%

    No Known Activations