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

    Neuronpedia

    INDEX
    Explanations

    LaTeX image formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    fton
    0.47
    raquo
    0.44
    icester
    0.38
     Ched
    0.37
     necesidades
    0.37
     obliged
    0.37
    heaven
    0.37
    市長
    0.37
    message
    0.36
     flyer
    0.36
    POSITIVE LOGITS
     nút
    0.40
    𝗸
    0.38
     تجاه
    0.38
    姩
    0.37
     naar
    0.36
     SKAction
    0.36
     pengaturan
    0.36
    呋
    0.36
     Towards
    0.35
     defaultdict
    0.35
    Act Density 0.000%

    No Known Activations