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

    Neuronpedia

    INDEX
    Explanations

    available

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    اغ
    -0.07
     mango
    -0.06
     Tort
    -0.06
     древ
    -0.06
    Oper
    -0.06
     가
    -0.06
    /Login
    -0.06
    opathy
    -0.06
     burgeoning
    -0.05
    mur
    -0.05
    POSITIVE LOGITS
     kov
    0.07
     vf
    0.07
     sinon
    0.07
    leading
    0.06
    -sharing
    0.06
    (sv
    0.06
    _ACTIV
    0.06
     assists
    0.06
    ريف
    0.06
    least
    0.06
    Act Density 0.002%

    No Known Activations