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

    Neuronpedia

    INDEX
    Explanations

    Conversational stories

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    HttpStatus
    -0.08
    utter
    -0.07
    تی
    -0.07
    一种
    -0.06
    apos
    -0.06
     uniformly
    -0.06
    REDIT
    -0.06
    World
    -0.06
    aries
    -0.06
    (World
    -0.06
    POSITIVE LOGITS
    」（
    0.06
    endif
    0.06
    .rstrip
    0.06
     Geneva
    0.06
     bzw
    0.06
     pruning
    0.06
    eksiyon
    0.06
    illusion
    0.06
    _uploaded
    0.05
     agitation
    0.05
    Act Density 0.035%

    No Known Activations