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

    Neuronpedia

    INDEX
    Explanations

    Says

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uits
    -0.07
     Madagascar
    -0.06
     Measurements
    -0.06
    Typography
    -0.06
    cloud
    -0.06
     attends
    -0.06
     SHE
    -0.06
    _Mod
    -0.06
    ourcing
    -0.06
     Compatible
    -0.06
    POSITIVE LOGITS
     ((((
    0.07
    电
    0.06
     sublic
    0.06
    Massage
    0.06
     jobId
    0.06
    >Nama
    0.06
     gebru
    0.06
    ];↵
    0.06
     khỏ
    0.06
     stitched
    0.06
    Act Density 0.033%

    No Known Activations