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

    Neuronpedia

    INDEX
    Explanations

    produce and herbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ///////////////
    0.46
     looser
    0.45
     los
    0.44
    карбо
    0.38
    න්නේ
    0.38
     provisioning
    0.38
    caption
    0.37
     Wyatt
    0.36
     quaisquer
    0.36
    Caption
    0.36
    POSITIVE LOGITS
    基本
    0.40
    衾
    0.39
    VED
    0.38
    Basic
    0.38
     基本
    0.38
    orh
    0.37
     رقم
    0.37
    »:
    0.37
    同学
    0.37
     básica
    0.37
    Act Density 0.000%

    No Known Activations