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

    Neuronpedia

    INDEX
    Explanations

    dirt

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ề
    -0.06
    WithString
    -0.06
    cision
    -0.06
    ůž
    -0.06
    상
    -0.06
    zych
    -0.06
    parison
    -0.06
     чого
    -0.06
    в
    -0.06
     महत
    -0.06
    POSITIVE LOGITS
    reload
    0.07
     Literary
    0.07
     "),
    0.07
    Growing
    0.06
    ...",
    0.06
     informational
    0.06
     �
    0.06
    Nickname
    0.06
     attest
    0.06
    cntl
    0.06
    Act Density 0.005%

    No Known Activations