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

    Neuronpedia

    INDEX
    Explanations

    Code/File paths

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     GENER
    -0.06
     вну
    -0.06
    ieu
    -0.06
     guests
    -0.06
     INSERT
    -0.06
     tie
    -0.06
     guest
    -0.06
     stiff
    -0.06
     RESULTS
    -0.06
     pus
    -0.06
    POSITIVE LOGITS
    andom
    0.07
    Sphere
    0.06
    890
    0.06
    ville
    0.06
    ovic
    0.06
    673
    0.06
     Stream
    0.06
     مورد
    0.06
    rypto
    0.06
    Lou
    0.06
    Act Density 0.131%

    No Known Activations