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

    Neuronpedia

    INDEX
    Explanations

    constant

    np_max-act · gemini-2.0-flash

    This neuron detects decimal number tokens (floating-point values).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Magn
    -0.06
     debugging
    -0.06
     Manage
    -0.06
     Manafort
    -0.06
    榜
    -0.06
     CDDL
    -0.06
    ažd
    -0.06
    profiles
    -0.05
    لال
    -0.05
     borders
    -0.05
    POSITIVE LOGITS
    .uk
    0.08
     використовувати
    0.07
    触
    0.07
    .unlink
    0.07
    ิศ
    0.07
     linguistic
    0.06
     крем
    0.06
     wealth
    0.06
    (bodyParser
    0.06
     Bool
    0.06
    Act Density 0.016%

    No Known Activations