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

    Neuronpedia

    INDEX
    Explanations

    list

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    gia
    -0.07
    oliday
    -0.07
    aways
    -0.06
    irable
    -0.06
    aturally
    -0.06
     hộp
    -0.06
    лата
    -0.06
    ta
    -0.06
     gritty
    -0.06
    _wo
    -0.06
    POSITIVE LOGITS
     Bliss
    0.07
     Samp
    0.06
    GetX
    0.06
     �
    0.06
     Beaut
    0.06
     Pom
    0.06
     listened
    0.06
     layer
    0.06
    (()=>{↵
    0.06
     Townsend
    0.06
    Act Density 0.001%

    No Known Activations