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

    Neuronpedia

    INDEX
    Explanations

    loops and repetition

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     scour
    -0.08
    �
    -0.07
    egend
    -0.07
    opr
    -0.07
    兜
    -0.07
    蔓延
    -0.06
     stupidity
    -0.06
    茅
    -0.06
    潆
    -0.06
    張
    -0.06
    POSITIVE LOGITS
    .addSubview
    0.08
    冲锋
    0.07
     Eisen
    0.07
     mientras
    0.07
     ра�
    0.07
     initState
    0.07
     rugged
    0.07
    �
    0.06
    武装
    0.06
    ssel
    0.06
    Act Density 0.018%

    No Known Activations