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

    Neuronpedia

    INDEX
    Explanations

    ),

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ческих
    -0.07
     праців
    -0.07
     dagger
    -0.07
     genie
    -0.07
     elles
    -0.06
    anker
    -0.06
    _band
    -0.06
    (post
    -0.06
    　 　 　 　 　 　
    -0.06
     이러한
    -0.06
    POSITIVE LOGITS
    earn
    0.07
    polation
    0.07
    ाफ
    0.06
     Forty
    0.06
     StringBuilder
    0.06
    .Transform
    0.06
    Expert
    0.06
    .Process
    0.06
    .ins
    0.06
    (Color
    0.06
    Act Density 0.005%

    No Known Activations