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

    Neuronpedia

    INDEX
    Explanations

    negative reviews

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    667
    -0.07
     Initialized
    -0.07
     scheme
    -0.07
    _predictions
    -0.06
    urons
    -0.06
     Dresses
    -0.06
    167
    -0.06
     processors
    -0.06
     سنت
    -0.06
     schemes
    -0.06
    POSITIVE LOGITS
     caret
    0.07
    /csv
    0.07
     nar
    0.07
     prolifer
    0.07
     eh
    0.07
     Grad
    0.06
    LINE
    0.06
    _at
    0.06
     MIT
    0.06
    VEL
    0.06
    Act Density 0.166%

    No Known Activations