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

    Neuronpedia

    INDEX
    Explanations

    `.zip` or `.mov`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    伎
    0.51
    rying
    0.50
    arh
    0.50
    ison
    0.50
    iendo
    0.49
    iye
    0.49
    ar
    0.48
    ation
    0.48
    क्षकों
    0.48
    hesion
    0.48
    POSITIVE LOGITS
     Hosts
    0.57
    س
    0.54
     Passion
    0.52
     Femin
    0.51
     Herb
    0.51
     হোস্ট
    0.49
    ד
    0.49
     Dose
    0.49
     Pharmac
    0.49
    ড
    0.49
    Act Density 0.000%

    No Known Activations