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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     onlara
    -0.06
     schwer
    -0.06
    .vector
    -0.06
    ớm
    -0.06
    roulette
    -0.06
    gravity
    -0.06
    Americans
    -0.06
     distraction
    -0.06
    脱
    -0.06
    -co
    -0.06
    POSITIVE LOGITS
    iology
    0.07
     Sword
    0.06
    iley
    0.06
    iculty
    0.06
    culo
    0.06
     looph
    0.06
     sword
    0.06
    sword
    0.06
    _WARNINGS
    0.06
    .cloudflare
    0.06
    Act Density 0.256%

    No Known Activations