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

    Neuronpedia

    INDEX
    Explanations

    key features and benefits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ১৮
    0.42
    thick
    0.39
    Love
    0.39
    throw
    0.39
    LOVE
    0.39
     دائو
    0.38
    DIV
    0.38
     fier
    0.37
    rapers
    0.36
     Tuck
    0.36
    POSITIVE LOGITS
     binary
    0.50
    binary
    0.47
     Binary
    0.44
    Binary
    0.43
     lames
    0.39
     প্রশ
    0.38
     badania
    0.38
     spider
    0.38
    廣場
    0.38
     அப்ப
    0.37
    Act Density 0.001%

    No Known Activations