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

    Neuronpedia

    INDEX
    Explanations

    structured text delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     particularly
    0.84
     especially
    0.66
     사용
    0.65
     though
    0.65
     settings
    0.65
     fi
    0.65
    的意思
    0.64
     버
    0.63
     퍼
    0.63
     kind
    0.63
    POSITIVE LOGITS
    Ꮧ
    0.77
    <caption>
    0.72
    ago
    0.72
     naciones
    0.71
    йде
    0.70
    iziModal
    0.69
    Ꮴ
    0.68
    স্থ
    0.67
    [['
    0.67
     mangiare
    0.66
    Act Density 0.930%

    No Known Activations