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

    Neuronpedia

    INDEX
    Explanations

    gems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Driver
    -0.07
     Census
    -0.07
    “As
    -0.07
     ingress
    -0.07
     (`
    -0.07
    activity
    -0.06
    _Part
    -0.06
    “When
    -0.06
     cycling
    -0.06
    '^
    -0.06
    POSITIVE LOGITS
     Jade
    0.10
     khuôn
    0.06
    寶
    0.06
     Maurit
    0.06
     jade
    0.06
    nak
    0.06
     diamond
    0.06
     виготов
    0.06
    aming
    0.06
     Boutique
    0.06
    Act Density 0.044%

    No Known Activations