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

    Neuronpedia

    INDEX
    Explanations

    role

    np_max-act · gemini-2.0-flash

    This neuron never activates—it doesn’t respond to any tokens.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     usa
    -0.07
     prosperous
    -0.07
    stinence
    -0.07
     dispon
    -0.07
    .disconnect
    -0.06
     occupying
    -0.06
    لی
    -0.06
    現在
    -0.06
     �
    -0.06
     allotted
    -0.06
    POSITIVE LOGITS
     retry
    0.06
     securely
    0.06
    Increment
    0.06
    skému
    0.06
     Minimum
    0.06
    .Resize
    0.06
     CALLBACK
    0.06
     Closed
    0.06
    -zero
    0.06
    ้าส
    0.06
    Act Density 0.069%

    No Known Activations