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

    Neuronpedia

    INDEX
    Explanations

    thing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     teg
    -0.07
    dong
    -0.07
     balk
    -0.07
     Küche
    -0.07
     cuda
    -0.07
     lei
    -0.06
    .pkg
    -0.06
    .wx
    -0.06
     fot
    -0.06
    caret
    -0.06
    POSITIVE LOGITS
    Skill
    0.07
    🗨
    0.07
     בשב
    0.07
    我们将
    0.07
    やす
    0.07
    .Account
    0.07
    安稳
    0.07
     ************************
    0.07
    áveis
    0.07
    ظم
    0.07
    Act Density 0.026%

    No Known Activations