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

    Neuronpedia

    INDEX
    Explanations

    learn

    np_max-act · gemini-2.0-flash

    The neuron never activates on any token, so it does not detect any specific pattern in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    �
    -0.07
     libertine
    -0.07
    Purpose
    -0.07
    .ma
    -0.06
    odied
    -0.06
     Male
    -0.06
    客户
    -0.06
     Hack
    -0.06
     collectively
    -0.06
    FINE
    -0.06
    POSITIVE LOGITS
    (tv
    0.07
     $?
    0.07
    ibName
    0.06
    .Localization
    0.06
    เคร
    0.06
     cantidad
    0.06
     deviceId
    0.06
     overshadow
    0.06
    :System
    0.06
    lights
    0.06
    Act Density 0.027%

    No Known Activations