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

    Neuronpedia

    INDEX
    Explanations

    Parentheses/brackets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Invisible
    -0.07
     такие
    -0.07
     matchups
    -0.06
     Married
    -0.06
    	Element
    -0.06
    ###↵
    -0.06
    阶段
    -0.06
    tempts
    -0.06
    .""
    -0.06
    斗
    -0.06
    POSITIVE LOGITS
    ierre
    0.07
     Ivy
    0.06
    ceil
    0.06
    颜
    0.06
    }}</
    0.06
    ****************************************************************
    0.06
     Cv
    0.06
    gradation
    0.06
    ICAST
    0.06
     Coach
    0.06
    Act Density 0.065%

    No Known Activations