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

    Neuronpedia

    INDEX
    Explanations

    alignment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Root
    -0.07
     $('#'
    -0.07
    _STA
    -0.07
     دن
    -0.07
    .look
    -0.06
     κατα
    -0.06
    サ
    -0.06
    ((↵
    -0.06
     Коли
    -0.06
     $("#"
    -0.06
    POSITIVE LOGITS
     crafting
    0.07
     Yugoslavia
    0.07
    ین
    0.06
     bullshit
    0.06
    *m
    0.06
    THIS
    0.06
             
    0.06
    —in
    0.06
    ��
    0.06
    ับการ
    0.06
    Act Density 0.004%

    No Known Activations