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

    Neuronpedia

    INDEX
    Explanations

    request for unsafe content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     StringBuffer
    0.41
     প্রভাস
    0.40
    数字化
    0.38
    առ
    0.38
    💿
    0.38
    ⛰
    0.38
    ▛
    0.38
     लेसन
    0.37
     exponentes
    0.37
     Schles
    0.36
    POSITIVE LOGITS
    ну
    0.38
     Peral
    0.37
    сс
    0.36
     j
    0.35
     salicylic
    0.35
     immoral
    0.34
     올
    0.34
     Musa
    0.33
    ataires
    0.33
     lethal
    0.33
    Act Density 0.054%

    No Known Activations