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

    Neuronpedia

    INDEX
    Explanations

    efficacy

    np_max-act · gemini-2.0-flash

    The neuron fires whenever the text is describing the measured efficacy or potency of a treatment, drug, or intervention.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Gün
    -0.07
     Blocks
    -0.07
     打
    -0.07
     Nuevo
    -0.07
    angen
    -0.07
    block
    -0.06
     neckline
    -0.06
    หนด
    -0.06
     Bernstein
    -0.06
     noticed
    -0.06
    POSITIVE LOGITS
     efficacy
    0.13
     proficiency
    0.08
     effic
    0.07
    _WAKE
    0.07
    Error
    0.07
    IFICATE
    0.07
    oric
    0.07
    ffic
    0.06
     savoir
    0.06
    (xhr
    0.06
    Act Density 0.005%

    No Known Activations