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

    Neuronpedia

    INDEX
    Explanations

    will

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     joker
    -0.07
     свят
    -0.06
    设
    -0.06
    �
    -0.06
     �
    -0.06
     có
    -0.06
    ิทธ
    -0.06
    ystone
    -0.06
    (old
    -0.06
    ��
    -0.06
    POSITIVE LOGITS
    _i
    0.06
    _line
    0.06
     machines
    0.06
    зація
    0.06
     edu
    0.06
    (":
    0.06
     Philosophy
    0.06
    leh
    0.06
    !;↵
    0.06
    awan
    0.06
    Act Density 0.042%

    No Known Activations