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

    Neuronpedia

    INDEX
    Explanations

    Considered a success/failure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     넣
    -0.06
    �
    -0.06
    ofil
    -0.06
    พบ
    -0.06
            ↵        ↵
    -0.06
     jogador
    -0.06
    furt
    -0.06
     authorities
    -0.06
    raj
    -0.05
     gift
    -0.05
    POSITIVE LOGITS
    riterion
    0.08
     */,
    0.07
     super
    0.07
     JOptionPane
    0.07
     четвер
    0.07
     Gothic
    0.07
    _part
    0.07
     offseason
    0.06
     sterling
    0.06
     alright
    0.06
    Act Density 0.054%

    No Known Activations