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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    extr
    -0.08
    fitness
    -0.07
     pint
    -0.07
    ：↵
    -0.07
     indispensable
    -0.07
    ⋼
    -0.06
     Champions
    -0.06
    izzer
    -0.06
    itness
    -0.06
     "");↵↵
    -0.06
    POSITIVE LOGITS
    ⚬
    0.08
    נב
    0.07
    Snake
    0.07
    ״
    0.07
     Tasks
    0.07
    蝠
    0.07
    /database
    0.06
     Background
    0.06
    璠
    0.06
    鲦
    0.06
    Act Density 0.185%

    No Known Activations