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

    Neuronpedia

    INDEX
    Explanations

    code/technical text

    np_max-act · gemini-2.0-flash

    This neuron specializes in detecting the word “storytelling” (and its sub‐token fragments).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ्त
    -0.07
     fw
    -0.06
     выбра
    -0.06
     pomp
    -0.06
    apellido
    -0.06
    ुत
    -0.06
    建築
    -0.06
    ationally
    -0.06
    ňuje
    -0.06
    naments
    -0.06
    POSITIVE LOGITS
     predominant
    0.06
    бург
    0.06
    169
    0.06
     лей
    0.06
    HASH
    0.06
     生命周期
    0.06
     Pain
    0.06
     PhoneNumber
    0.05
     Qualcomm
    0.05
    .views
    0.05
    Act Density 0.176%

    No Known Activations