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

    Neuronpedia

    INDEX
    Explanations

    code variables

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     प्रक
    -0.09
    寻找
    -0.08
    租
    -0.08
    issy
    -0.08
     carve
    -0.08
    ेस्ट
    -0.08
    ancas
    -0.08
    李
    -0.08
     тиб
    -0.08
    侵犯
    -0.08
    POSITIVE LOGITS
     consciente
    0.07
     Conditional
    0.07
     широк
    0.07
     service
    0.07
    ંભ
    0.07
     conscientes
    0.07
    まあ
    0.07
     Cruc
    0.07
     Practical
    0.07
     quite
    0.07
    Act Density 0.000%

    No Known Activations