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

    Neuronpedia

    INDEX
    Explanations

    про

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vela
    -0.08
    nda
    -0.08
    fuscated
    -0.08
     Fo
    -0.08
     misleading
    -0.07
     curl
    -0.07
    思
    -0.07
    榜
    -0.07
    Authent
    -0.07
     ronda
    -0.07
    POSITIVE LOGITS
     Fra
    0.09
     Wy
    0.08
    Wy
    0.08
     />
    0.07
    �
    0.07
     wys
    0.07
     ‚
    0.07
     Hay
    0.07
     peoples
    0.07
    им
    0.07
    Act Density 0.001%

    No Known Activations