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

    Neuronpedia

    INDEX
    Explanations

    key differentiator

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    判断
    0.59
    เต
    0.57
     чувства
    0.56
     declaraciones
    0.56
     Mystery
    0.55
     solicitor
    0.55
     símbolos
    0.54
    確認
    0.54
     simbol
    0.54
    社員
    0.54
    POSITIVE LOGITS
     architectures
    1.16
     computationally
    1.14
     GPUs
    1.05
     computational
    1.03
     technologies
    1.01
     researchers
    1.01
     advancements
    1.00
     TensorFlow
    0.98
     연구
    0.95
     developers
    0.95
    Act Density 1.933%

    No Known Activations