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

    Neuronpedia

    INDEX
    Explanations

    >

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    带åĽŀ
    -0.28
    spin
    -0.26
    qd
    -0.26
    æ´²
    -0.26
    æ¯ħ
    -0.26
    kad
    -0.25
    çĬ¶
    -0.25
    east
    -0.25
    é£İ
    -0.25
     misplaced
    -0.24
    POSITIVE LOGITS
    éª
    0.28
     Taco
    0.27
    .toJSON
    0.27
    ç³
    0.25
    casting
    0.25
    -syntax
    0.25
     anonym
    0.25
    幡
    0.25
    åĽłä¸ºå¥¹
    0.24
    amat
    0.24
    Act Density 0.004%

    No Known Activations