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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash

    This neuron activates on verbs describing job‐related duties or actions (e.g. manage, communicate, attend, receive, consult).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     olabilir
    -0.07
    attached
    -0.06
    状态
    -0.06
     hijos
    -0.06
    810
    -0.06
     benefici
    -0.06
     laptop
    -0.06
    412
    -0.06
     Laptop
    -0.06
     Capacity
    -0.06
    POSITIVE LOGITS
    няв
    0.07
    訂
    0.07
    ﺘ
    0.06
    .group
    0.06
    磨
    0.06
    /plain
    0.06
    λαν
    0.06
    سة
    0.06
    的手
    0.06
    麦
    0.06
    Act Density 0.135%

    No Known Activations