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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     xm
    -0.08
    Ꮆ
    -0.08
    🏙
    -0.07
     Clover
    -0.07
    abs
    -0.07
    🇰
    -0.07
    胗
    -0.07
     trans
    -0.07
    年之
    -0.07
    _rp
    -0.07
    POSITIVE LOGITS
    mia
    0.07
     courteous
    0.07
     goalkeeper
    0.07
    Although
    0.07
     Lord
    0.07
    멎
    0.07
     Employees
    0.07
    以后
    0.07
    auważ
    0.06
     그러나
    0.06
    Act Density 0.006%

    No Known Activations