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

    Neuronpedia

    INDEX
    Explanations

    picking

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric probability values (decimal numbers and fractions) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .cond
    -0.07
    Equip
    -0.07
     �
    -0.07
    Train
    -0.06
     probes
    -0.06
    lete
    -0.06
     sucht
    -0.06
    독
    -0.06
    _No
    -0.06
     Marin
    -0.06
    POSITIVE LOGITS
    thora
    0.08
    |↵
    0.08
    (criteria
    0.08
    砲
    0.07
    jas
    0.07
    目录
    0.07
    接着
    0.07
     wildlife
    0.07
    abilidade
    0.07
    asury
    0.06
    Act Density 0.001%

    No Known Activations