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

    Neuronpedia

    INDEX
    Explanations

    code about semicolons

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    不得超过
    -0.07
     ARISING
    -0.07
     세상
    -0.07
    -random
    -0.07
    طرف
    -0.07
    说过
    -0.06
    就近
    -0.06
    (context
    -0.06
    urther
    -0.06
    将近
    -0.06
    POSITIVE LOGITS
    ℓ
    0.07
    鿎
    0.07
    mgr
    0.07
    .cmb
    0.07
     simul
    0.06
    (rt
    0.06
    造型
    0.06
     assassin
    0.06
     ".
    0.06
    _usr
    0.06
    Act Density 0.007%

    No Known Activations