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

    Neuronpedia

    INDEX
    Explanations

    References

    np_max-act · gemini-2.0-flash

    This neuron detects numeric values written with decimal points (i.e. floating-point numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .E
    -0.07
    ैज
    -0.06
    _corners
    -0.06
    'I
    -0.06
    ados
    -0.06
    ША
    -0.06
    ělí
    -0.06
     tol
    -0.06
     Stamp
    -0.06
    Ш
    -0.06
    POSITIVE LOGITS
    implicitly
    0.07
    .asarray
    0.06
     ArrayAdapter
    0.06
     realloc
    0.06
     раствор
    0.06
    .awt
    0.06
     ]];
    0.06
    .au
    0.06
    dělení
    0.06
     بندی
    0.06
    Act Density 0.054%

    No Known Activations