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

    Neuronpedia

    INDEX
    Explanations

    code and data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Age
    -0.07
     κον
    -0.07
     exhibition
    -0.07
     ripe
    -0.07
    .StretchImage
    -0.07
    utting
    -0.07
    anth
    -0.06
     advertisement
    -0.06
     blasted
    -0.06
     Minneapolis
    -0.06
    POSITIVE LOGITS
     Chew
    0.06
     infield
    0.05
    crement
    0.05
    Simple
    0.05
    atile
    0.05
    tracker
    0.05
     WRITE
    0.05
    �
    0.05
    心里
    0.05
    fileName
    0.05
    Act Density 0.001%

    No Known Activations