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

    Neuronpedia

    INDEX
    Explanations

    pare

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ja
    -0.07
    Arizona
    -0.06
    clarsimp
    -0.06
     suggestions
    -0.06
     imagem
    -0.06
     Exercise
    -0.06
    еви
    -0.06
    toolbox
    -0.06
     pochop
    -0.06
     επ
    -0.06
    POSITIVE LOGITS
     mingle
    0.07
     AE
    0.07
    ousel
    0.06
    Anne
    0.06
     donn
    0.06
     Hoover
    0.06
    ael
    0.06
     initialValue
    0.06
    �
    0.06
     gauss
    0.06
    Act Density 0.003%

    No Known Activations