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

    Neuronpedia

    INDEX
    Explanations

    fees

    np_max-act · gemini-2.0-flash

    The neuron consistently activates on monetary amounts—especially court filing‐fee figures and related dollar values.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _Register
    -0.08
     Criteria
    -0.07
     Twe
    -0.07
     Fab
    -0.07
     Herbert
    -0.07
     celle
    -0.07
     candidates
    -0.06
     SCREEN
    -0.06
     FIND
    -0.06
     Channel
    -0.06
    POSITIVE LOGITS
    λα
    0.06
    ipro
    0.06
                 ↵
    0.06
    unted
    0.06
    >↵
    0.06
    три
    0.06
    _MAPPING
    0.06
     Louisville
    0.06
    charge
    0.06
    ENARIO
    0.06
    Act Density 0.003%

    No Known Activations