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

    Neuronpedia

    INDEX
    Explanations

    punctuation and "and"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     KO
    -0.08
    )obj
    -0.07
    utterstock
    -0.07
    .po
    -0.07
    _LT
    -0.07
     Avoid
    -0.07
    overnment
    -0.07
    rowning
    -0.06
     MO
    -0.06
     Perhaps
    -0.06
    POSITIVE LOGITS
     eased
    0.06
     productName
    0.06
    _protocol
    0.06
     松
    0.06
     },↵
    0.06
    ダ
    0.06
     revealing
    0.05
    .ct
    0.05
    기간
    0.05
     banged
    0.05
    Act Density 0.005%

    No Known Activations