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

    Neuronpedia

    INDEX
    Explanations

    future plans

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    metatable
    -0.07
     querying
    -0.07
    _ex
    -0.06
     Exception
    -0.06
    ерг
    -0.06
     weak
    -0.06
    ộn
    -0.06
     recht
    -0.06
     slide
    -0.06
    ite
    -0.06
    POSITIVE LOGITS
     Львів
    0.07
    ायत
    0.06
     zih
    0.06
     fs
    0.06
     infancy
    0.06
     senin
    0.06
     HF
    0.06
    orch
    0.06
     Hawth
    0.06
     نادي
    0.06
    Act Density 0.026%

    No Known Activations