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

    Neuronpedia

    INDEX
    Explanations

    Biographies

    np_max-act · gemini-2.0-flash

    This neuron detects romanized Chinese name components.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Ampl
    -0.08
    ARRY
    -0.07
    Mus
    -0.07
     heirs
    -0.06
    PL
    -0.06
     meat
    -0.06
    �y
    -0.06
     tcb
    -0.06
    vehicle
    -0.06
    _migration
    -0.06
    POSITIVE LOGITS
    Uploaded
    0.07
    .cursor
    0.07
    ]",
    0.06
    ー
    0.06
    Prediction
    0.06
    並
    0.06
     intuition
    0.06
    arseille
    0.06
     збір
    0.06
     �
    0.06
    Act Density 0.061%

    No Known Activations