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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     quicker
    -0.06
     rud
    -0.06
    itu
    -0.06
    aines
    -0.06
     thang
    -0.05
    />.↵↵
    -0.05
     Gaut
    -0.05
    хран
    -0.05
     кус
    -0.05
    estone
    -0.05
    POSITIVE LOGITS
    799
    0.07
     определен
    0.07
     electoral
    0.07
    β
    0.07
    _SUB
    0.07
    แบ
    0.07
     그런
    0.07
     consumes
    0.07
    기준
    0.07
    034
    0.06
    Act Density 4.037%

    No Known Activations