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

    Neuronpedia

    INDEX
    Explanations

    code and programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .contrib
    -0.08
     Inn
    -0.07
     Copp
    -0.07
     staunch
    -0.07
    .Dark
    -0.07
     Hass
    -0.06
     dél
    -0.06
    attr
    -0.06
    学院
    -0.06
     Huff
    -0.06
    POSITIVE LOGITS
    aternion
    0.06
     setName
    0.06
     errorThrown
    0.06
     placing
    0.06
    RAM
    0.06
    综合
    0.06
     shields
    0.06
     detects
    0.06
     (!
    0.06
    ToList
    0.06
    Act Density 0.000%

    No Known Activations