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

    Neuronpedia

    INDEX
    Explanations

    code structures and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    abe
    0.87
    obby
    0.83
     shrugged
    0.79
     depres
    0.77
     hedging
    0.77
    vpc
    0.77
     बालो
    0.76
     hurricanes
    0.75
     choking
    0.75
    띵
    0.75
    POSITIVE LOGITS
     등이
    0.79
     executar
    0.73
     등으로
    0.72
    |
    0.71
     «
    0.71
    )|
    0.71
     тощо
    0.68
    などを
    0.67
    ת
    0.67
     등을
    0.66
    Act Density 1.211%

    No Known Activations