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

    Neuronpedia

    INDEX
    Explanations

    199

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _n
    -0.07
     Wife
    -0.07
     Voll
    -0.07
    цієн
    -0.07
    Gb
    -0.07
     crab
    -0.06
    هور
    -0.06
    �
    -0.06
    čná
    -0.06
     Heg
    -0.06
    POSITIVE LOGITS
    (FILE
    0.08
    filename
    0.07
     comprehension
    0.07
     advertisement
    0.07
    /com
    0.06
     bankruptcy
    0.06
    <<<<
    0.06
    (artist
    0.06
     Giles
    0.06
    україн
    0.06
    Act Density 0.002%

    No Known Activations