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

    Neuronpedia

    INDEX
    Explanations

    al

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _chr
    -0.07
    .Startup
    -0.07
    นาน
    -0.07
     buff
    -0.07
     Univers
    -0.07
    饽
    -0.07
    消毒
    -0.07
     Crunch
    -0.07
    genres
    -0.07
    _cred
    -0.07
    POSITIVE LOGITS
    قاء
    0.07
    entarios
    0.07
     få
    0.07
    uns
    0.07
    volução
    0.07
    eterangan
    0.06
    da
    0.06
    遷
    0.06
    )data
    0.06
     وحتى
    0.06
    Act Density 0.006%

    No Known Activations