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

    Neuronpedia

    INDEX
    Explanations

    ``

    np_max-act · gemini-2.0-flash

    This neuron detects emoji or other non-alphanumeric symbol tokens (i.e., pictographic characters).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     curt
    -0.08
    Page
    -0.07
    itus
    -0.07
     staging
    -0.07
     Force
    -0.07
     Tenant
    -0.07
    	FOR
    -0.07
     Craw
    -0.07
     Station
    -0.07
    assword
    -0.07
    POSITIVE LOGITS
     �
    0.10
    �
    0.08
     │
    0.06
     сила
    0.06
    gamma
    0.06
     θα
    0.06
     inequalities
    0.06
     RTAL
    0.06
    σιμο
    0.06
    ความ
    0.06
    Act Density 0.009%

    No Known Activations