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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash

    The neuron responds to numeric tokens (digits and numbered placeholders).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     takdir
    -0.06
    .drawer
    -0.06
    έλ
    -0.06
    大人
    -0.06
    Authorization
    -0.06
    -io
    -0.06
    羊
    -0.06
    esinin
    -0.06
    Arr
    -0.06
    ilerinin
    -0.06
    POSITIVE LOGITS
     resize
    0.07
    (lista
    0.07
    став
    0.07
    ΟΙ
    0.06
    рования
    0.06
    membership
    0.06
     Logo
    0.06
     schemas
    0.06
     Binding
    0.06
     Sales
    0.06
    Act Density 0.035%

    No Known Activations