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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     presenter
    -0.08
     [↵↵
    -0.07
    ttl
    -0.06
    rane
    -0.06
     laser
    -0.06
     crowded
    -0.06
     ${(
    -0.06
     고려
    -0.06
    minating
    -0.06
    身份
    -0.06
    POSITIVE LOGITS
    _chars
    0.07
    ैद
    0.06
     चर
    0.06
     downt
    0.06
     bootstrap
    0.06
     native
    0.06
     ル
    0.06
    Cum
    0.06
     Terms
    0.06
     subcontract
    0.06
    Act Density 0.033%

    No Known Activations