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

    Neuronpedia

    INDEX
    Explanations

    Technical descriptions

    np_max-act · gemini-2.0-flash

    The neuron primarily detects mentions of “bits” (including quantum‐bit terms like “qubits,” “Qubits,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    По
    -0.07
     extracting
    -0.06
     тем
    -0.06
     lun
    -0.06
    �
    -0.06
    .TOP
    -0.06
    .opt
    -0.06
    /object
    -0.06
    /un
    -0.06
    ielding
    -0.06
    POSITIVE LOGITS
     colorful
    0.07
    'Connor
    0.07
    identification
    0.07
    ('').
    0.06
    대를
    0.06
     giành
    0.06
     Third
    0.06
     httpRequest
    0.06
    (!_
    0.06
    .descripcion
    0.06
    Act Density 0.019%

    No Known Activations