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

    Neuronpedia

    INDEX
    Explanations

    Coding and real-world comparisons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     posicion
    -0.09
     ating
    -0.07
    =False
    -0.07
     lloc
    -0.07
     analysis
    -0.07
    PI
    -0.07
     hiding
    -0.07
     secrecy
    -0.07
     subjects
    -0.07
     aircraft
    -0.07
    POSITIVE LOGITS
     tjenester
    0.08
    lossen
    0.08
     Höhen
    0.08
     вона
    0.08
    iningi
    0.08
     ymin
    0.08
    udla
    0.08
     yim
    0.08
    ianza
    0.07
    ADF
    0.07
    Act Density 0.000%

    No Known Activations