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

    Neuronpedia

    INDEX
    Explanations

    reasons

    np_max-act · gemini-2.0-flash

    the word “because,” i.e. causal conjunctions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     관
    -0.07
     thứ
    -0.06
    [MAX
    -0.06
     Terminal
    -0.06
    .limit
    -0.06
     Records
    -0.06
    Inicio
    -0.06
     Mystery
    -0.06
    год
    -0.06
     VS
    -0.06
    POSITIVE LOGITS
    asking
    0.07
     Romania
    0.07
     intermitt
    0.06
     deposition
    0.06
    rc
    0.06
     Singular
    0.06
     případě
    0.06
    ensi
    0.06
    _conv
    0.06
     remarked
    0.06
    Act Density 0.049%

    No Known Activations