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

    Neuronpedia

    INDEX
    Explanations

    software development code/config

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ，你
    -0.07
    ає
    -0.06
    inst
    -0.06
    wire
    -0.06
    hero
    -0.06
     revenge
    -0.06
    entric
    -0.06
    elyn
    -0.06
     metropolitan
    -0.06
     dental
    -0.06
    POSITIVE LOGITS
    modele
    0.06
    ندق
    0.06
    Summon
    0.06
    FullScreen
    0.06
    _FAILED
    0.06
    NIEnv
    0.06
     dive
    0.06
    (sz
    0.06
     muschi
    0.06
    .curr
    0.06
    Act Density 0.079%

    No Known Activations