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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    achten
    -0.08
     demanding
    -0.08
    Moreover
    -0.07
    )>=
    -0.07
    -record
    -0.07
     Snowden
    -0.07
     onde
    -0.07
    -sign
    -0.07
    Names
    -0.07
    .Tests
    -0.07
    POSITIVE LOGITS
     dato
    0.07
     visibly
    0.07
    _sibling
    0.07
    phant
    0.07
     Blessed
    0.06
     WHY
    0.06
    _TI
    0.06
    abbr
    0.06
     ARCH
    0.06
     sliced
    0.06
    Act Density 0.001%

    No Known Activations