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

    Neuronpedia

    INDEX
    Explanations

    weekend

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     orada
    -0.07
    ------
    -0.06
    yní
    -0.06
     naší
    -0.06
    directory
    -0.06
    uria
    -0.06
     рос
    -0.06
    F
    -0.06
     boosts
    -0.06
    nih
    -0.06
    POSITIVE LOGITS
    ensem
    0.07
    도를
    0.07
     ideologies
    0.07
     vlak
    0.06
    ้าม
    0.06
    식을
    0.06
     wager
    0.06
     Snap
    0.06
     cảm
    0.06
     createSelector
    0.06
    Act Density 0.007%

    No Known Activations