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

    Neuronpedia

    INDEX
    Explanations

    mathematics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Johnson
    -0.07
    971
    -0.07
    部门
    -0.07
     GUIDE
    -0.06
    252
    -0.06
    %.
    -0.06
     among
    -0.06
     mh
    -0.06
    세
    -0.06
    Seven
    -0.06
    POSITIVE LOGITS
    üml
    0.07
    êt
    0.07
    InstanceState
    0.07
    Ao
    0.06
    ımız
    0.06
     secara
    0.06
    érieur
    0.06
    λλη
    0.06
    _timeout
    0.06
    loi
    0.06
    Act Density 0.008%

    No Known Activations