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

    Neuronpedia

    INDEX
    Explanations

    algorithms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    они
    -0.06
    Bru
    -0.06
     mountains
    -0.06
    ay
    -0.06
     clothing
    -0.06
    ustum
    -0.06
    [List
    -0.06
     acquitted
    -0.06
    _POOL
    -0.06
     história
    -0.06
    POSITIVE LOGITS
    (*)(
    0.06
     babel
    0.06
     reloc
    0.06
    �
    0.06
    %"><
    0.06
     област
    0.06
    ★★
    0.06
     Titans
    0.06
    igham
    0.06
    ครงการ
    0.06
    Act Density 0.064%

    No Known Activations