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

    Neuronpedia

    INDEX
    Explanations

    statements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tou
    -0.07
    计
    -0.06
    발
    -0.06
    ureau
    -0.06
    .horizontal
    -0.06
     đẹp
    -0.06
    endif
    -0.06
    .links
    -0.06
     angels
    -0.06
     блок
    -0.06
    POSITIVE LOGITS
    』↵↵
    0.07
     Sug
    0.07
     merkez
    0.07
    割
    0.07
    持
    0.06
    -ver
    0.06
    �
    0.06
     zru
    0.06
    �
    0.06
     intuition
    0.06
    Act Density 0.006%

    No Known Activations