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

    Neuronpedia

    INDEX
    Explanations

    according to

    np_max-act · gemini-2.0-flash

    The neuron fires on phrases attributing information to a source—especially “According to X”‐style citations.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ！”
    -0.07
    uncio
    -0.07
    ingga
    -0.07
     AttributeSet
    -0.07
    $v
    -0.07
    IsRequired
    -0.06
    —if
    -0.06
    .Mesh
    -0.06
    افية
    -0.06
    assessment
    -0.06
    POSITIVE LOGITS
     toho
    0.06
    (secret
    0.06
    stacle
    0.06
     sb
    0.06
    อด
    0.06
     discontinued
    0.06
    λης
    0.06
     ps
    0.06
    (angle
    0.06
     Eine
    0.06
    Act Density 0.047%

    No Known Activations