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

    Neuronpedia

    INDEX
    Explanations

    lack of something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     THIS
    0.22
     this
    0.20
     ($
    0.20
     isotherms
    0.20
     enables
    0.19
     along
    0.19
     ("
    0.18
    ต่างๆ
    0.18
    atios
    0.18
    atypes
    0.18
    POSITIVE LOGITS
    真正的
    0.23
    主动
    0.20
    明确
    0.20
     குறிப்பிட்டு
    0.20
     언급
    0.20
     siquiera
    0.20
    真正
    0.19
    提及
    0.19
    ственная
    0.19
     alcuna
    0.19
    Act Density 0.986%

    No Known Activations