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

    Neuronpedia

    INDEX
    Explanations

    Initials of people's names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    بی
    -0.07
     يجب
    -0.07
     yer
    -0.06
     �
    -0.06
    aryawan
    -0.06
    WithPath
    -0.06
    _ctl
    -0.06
     slav
    -0.06
    fake
    -0.06
    Netflix
    -0.06
    POSITIVE LOGITS
    楽
    0.07
    OWNER
    0.06
    消
    0.06
     breaks
    0.06
    (IC
    0.06
    _face
    0.06
     strides
    0.06
    owners
    0.06
    ��
    0.06
    #echo
    0.06
    Act Density 0.008%

    No Known Activations