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

    Neuronpedia

    INDEX
    Explanations

    not

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pimp
    -0.08
    ixture
    -0.07
    technical
    -0.07
    윰
    -0.07
    مين
    -0.07
    istr
    -0.07
    忡
    -0.07
    Straight
    -0.07
     south
    -0.07
    梅西
    -0.07
    POSITIVE LOGITS
     nossa
    0.07
     Anatomy
    0.07
    индивиду
    0.06
     labour
    0.06
    므로
    0.06
     restrained
    0.06
     Stim
    0.06
     Sag
    0.06
     Lif
    0.06
    仍未
    0.06
    Act Density 0.005%

    No Known Activations