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

    Neuronpedia

    INDEX
    Explanations

    hyphens

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric tokens representing precise decimal values (i.e., floating-point numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ��
    -0.06
    脂
    -0.06
    、↵
    -0.06
    因
    -0.06
    foobar
    -0.06
     Ted
    -0.05
    -copy
    -0.05
    身
    -0.05
    (ic
    -0.05
     sobě
    -0.05
    POSITIVE LOGITS
    Contract
    0.07
     occupations
    0.07
     adventurer
    0.07
    )_
    0.07
    opis
    0.06
     nouveaux
    0.06
    Category
    0.06
    했다
    0.06
    ンディ
    0.06
    minimal
    0.06
    Act Density 0.004%

    No Known Activations