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

    Neuronpedia

    INDEX
    Explanations

    time passing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    $this
    -0.07
     developer
    -0.07
    axter
    -0.06
     capability
    -0.06
    Must
    -0.06
    elloworld
    -0.06
    predicate
    -0.06
     ctr
    -0.06
    �
    -0.06
     accumulating
    -0.06
    POSITIVE LOGITS
    arrings
    0.07
    öff
    0.06
    .Copy
    0.06
     ISA
    0.06
     annually
    0.06
     fairly
    0.06
    Beyond
    0.06
     grátis
    0.06
     Beyond
    0.06
     akin
    0.06
    Act Density 0.041%

    No Known Activations