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

    Neuronpedia

    INDEX
    Explanations

    markdown plain text syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    问题
    0.49
    жда
    0.46
    Ciudad
    0.46
    这里
    0.45
    Une
    0.44
    Фа
    0.43
    Trinity
    0.42
    Más
    0.41
    创业
    0.40
    CBD
    0.40
    POSITIVE LOGITS
     removes
    0.56
     adhesives
    0.51
     allows
    0.50
     facilitates
    0.49
     prefixes
    0.49
     slats
    0.47
     enables
    0.46
     beverages
    0.46
     number
    0.46
     indicates
    0.46
    Act Density 0.002%

    No Known Activations