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

    Neuronpedia

    INDEX
    Explanations

    insects

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .perform
    -0.07
     Định
    -0.07
    ượt
    -0.07
     Bieber
    -0.07
    脱
    -0.07
     buildings
    -0.06
     hotel
    -0.06
    _EMIT
    -0.06
     PhoneNumber
    -0.06
     people
    -0.06
    POSITIVE LOGITS
    合わせ
    0.08
    amaged
    0.07
     compliant
    0.07
    .agent
    0.07
    致します
    0.07
     Portable
    0.07
    Parts
    0.07
     subur
    0.06
    付き合
    0.06
    	ff
    0.06
    Act Density 0.152%

    No Known Activations