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

    Neuronpedia

    INDEX
    Explanations

    introduction for applications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kinda
    0.90
     そして
    0.89
     ก็
    0.88
     isn
    0.86
     และ
    0.85
     まあ
    0.84
     ហើយ
    0.84
     didn
    0.84
     ถ้า
    0.84
     seems
    0.83
    POSITIVE LOGITS
    The
    1.02
    Initial
    0.99
    According
    0.99
    Initially
    0.98
    Originally
    0.95
    Re
    0.94
    R
    0.93
    Jane
    0.92
    No
    0.90
    In
    0.89
    Act Density 0.028%

    No Known Activations