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

    Neuronpedia

    INDEX
    Explanations

    to, on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     přev
    -0.08
    -history
    -0.07
     akci
    -0.07
     condemnation
    -0.07
     succès
    -0.06
     кирп
    -0.06
     receber
    -0.06
     especific
    -0.06
     rừng
    -0.06
     assertNull
    -0.06
    POSITIVE LOGITS
     realizing
    0.07
    ulator
    0.07
    ERING
    0.07
    �게
    0.07
     pan
    0.06
    uing
    0.06
    ัพย
    0.06
    من
    0.06
    Tokens
    0.06
    λλα
    0.06
    Act Density 0.014%

    No Known Activations