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

    Neuronpedia

    INDEX
    Explanations

    instructions/suggestions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ubuntu
    -0.07
     automotive
    -0.07
     Employer
    -0.07
     Likely
    -0.07
     бук
    -0.06
     Assembly
    -0.06
     Expansion
    -0.06
     dash
    -0.06
     former
    -0.06
     excit
    -0.06
    POSITIVE LOGITS
     грн
    0.07
     INCIDENTAL
    0.06
    鎮
    0.06
     tetas
    0.06
    верж
    0.06
     υπάρχουν
    0.06
     lø
    0.06
    orum
    0.05
    _IList
    0.05
    VP
    0.05
    Act Density 0.133%

    No Known Activations