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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    alk
    -0.07
     využí
    -0.07
    /python
    -0.07
     Fake
    -0.07
     Franco
    -0.06
    Pont
    -0.06
     andra
    -0.06
     azal
    -0.06
    Title
    -0.06
    793
    -0.06
    POSITIVE LOGITS
    AtPath
    0.06
    ीट
    0.06
     tác
    0.06
     womb
    0.06
    بت
    0.05
    _dc
    0.05
    .assertNotNull
    0.05
     (!$
    0.05
    ตอบ
    0.05
     drunken
    0.05
    Act Density 0.110%

    No Known Activations