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

    Neuronpedia

    INDEX
    Explanations

    ir

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Stephen
    -0.07
     Winner
    -0.07
    الية
    -0.07
     Norway
    -0.07
     Gy
    -0.06
    Stephen
    -0.06
     golf
    -0.06
    415
    -0.06
     bleibt
    -0.06
     없이
    -0.06
    POSITIVE LOGITS
    _REFER
    0.07
    ir
    0.06
    IR
    0.06
    .AutoSizeMode
    0.06
    たり
    0.06
    luğ
    0.06
    등
    0.06
    者の
    0.06
    -posts
    0.06
    ерату
    0.06
    Act Density 0.006%

    No Known Activations