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

    Neuronpedia

    INDEX
    Explanations

    `import dataclass`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    nmid
    0.46
     przyczyn
    0.41
     Wills
    0.40
    野
    0.40
     búsqueda
    0.39
    IGN
    0.37
     गोर
    0.37
     вопло
    0.36
    य़ा
    0.36
     الماس
    0.36
    POSITIVE LOGITS
     antigen
    0.50
     Antigen
    0.48
     preferential
    0.41
     antigens
    0.40
     Ag
    0.40
     Hipp
    0.40
     অ্যান্টি
    0.39
     stallion
    0.38
     शौक
    0.38
     questionable
    0.38
    Act Density 0.000%

    No Known Activations