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

    Neuronpedia

    INDEX
    Explanations

    we will

    np_max-act · gemini-2.0-flash

    This neuron detects the conclusion/disposition phrases in a legal opinion—i.e. the “We affirm,” “We reverse,” “Accordingly,” and similar judgment‐ending statements.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     �
    -0.06
     Notifications
    -0.06
    BracketAccess
    -0.06
    図
    -0.06
     Suc
    -0.06
     conseguir
    -0.06
    .Components
    -0.06
     Cri
    -0.06
     Lex
    -0.06
    ambre
    -0.06
    POSITIVE LOGITS
    cbd
    0.07
     chiến
    0.06
     офі
    0.06
    ành
    0.06
     java
    0.06
    189
    0.06
     kì
    0.06
    _SELECTED
    0.06
    �
    0.06
     fighters
    0.06
    Act Density 0.008%

    No Known Activations