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

    Neuronpedia

    INDEX
    Explanations

    leet speak

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     μέρος
    -0.07
     Reve
    -0.06
     Australia
    -0.06
    ада
    -0.06
    엇
    -0.06
     αστ
    -0.06
     τ
    -0.06
     густ
    -0.06
     Bugün
    -0.06
     Singapore
    -0.06
    POSITIVE LOGITS
    Cached
    0.07
     commencement
    0.07
     plaintext
    0.06
     inline
    0.06
    inline
    0.06
    _dice
    0.06
    dl
    0.06
     redeemed
    0.06
    Placement
    0.06
    rng
    0.06
    Act Density 0.043%

    No Known Activations