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

    Neuronpedia

    INDEX
    Explanations

    code and articles

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    🖌
    -0.07
     بط
    -0.07
    Service
    -0.07
    Off
    -0.07
    下来
    -0.07
     leg
    -0.07
    routeParams
    -0.07
    May
    -0.07
     Glass
    -0.07
     bele
    -0.07
    POSITIVE LOGITS
     proponents
    0.07
    <G
    0.07
     $$
    0.07
     EEPROM
    0.07
    iel
    0.07
     principle
    0.07
    iac
    0.07
     Central
    0.06
    侦查
    0.06
     prosecutor
    0.06
    Act Density 0.084%

    No Known Activations