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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Kaplan
    -0.08
    ⤦
    -0.07
     względ
    -0.07
    Ḝ
    -0.07
    ᠆
    -0.07
     Moor
    -0.07
     الإنسان
    -0.07
     Sri
    -0.07
    )))),
    -0.07
    Видео
    -0.07
    POSITIVE LOGITS
    髫
    0.07
     dro
    0.07
    早
    0.06
    ग
    0.06
    numbers
    0.06
    iddled
    0.06
    이
    0.06
    几家
    0.06
    万亿元
    0.06
     ücrets
    0.06
    Act Density 0.041%

    No Known Activations