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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .�
    -0.07
     strconv
    -0.07
    iştir
    -0.07
    ただ
    -0.06
    .ops
    -0.06
     wäre
    -0.06
    模
    -0.06
     eh
    -0.06
    ยก
    -0.06
     нічого
    -0.06
    POSITIVE LOGITS
     lime
    0.08
     verso
    0.07
    vincia
    0.07
     Luna
    0.07
     Bags
    0.06
    abolic
    0.06
    umm
    0.06
    /about
    0.06
     Underground
    0.06
     Advance
    0.06
    Act Density 0.000%

    No Known Activations