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

    Neuronpedia

    INDEX
    Explanations

    Throughout

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ingress
    -0.07
     capacities
    -0.07
     stronger
    -0.06
     relative
    -0.06
     answers
    -0.06
     Asian
    -0.06
     Receiver
    -0.06
     ADDR
    -0.06
     Alexa
    -0.06
    renders
    -0.06
    POSITIVE LOGITS
     throughout
    0.10
    Throughout
    0.09
    lanmıştır
    0.08
     �
    0.07
     Throughout
    0.07
     bou
    0.07
    .boot
    0.07
    往
    0.07
     har
    0.06
    .getTime
    0.06
    Act Density 0.010%

    No Known Activations