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

    Neuronpedia

    INDEX
    Explanations

    It

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ічна
    -0.07
     pager
    -0.06
    Styles
    -0.06
    ergy
    -0.06
     crane
    -0.06
    想到
    -0.06
    ites
    -0.06
    媒体
    -0.06
    UserId
    -0.05
    (TypeError
    -0.05
    POSITIVE LOGITS
     병
    0.08
     सक
    0.08
    /md
    0.07
    _mot
    0.07
    _PICK
    0.07
     sanct
    0.06
     محصولات
    0.06
     �
    0.06
    .Directory
    0.06
    เพลง
    0.06
    Act Density 0.043%

    No Known Activations