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

    Neuronpedia

    INDEX
    Explanations

    varied text snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    characters
    -0.07
     uu
    -0.07
     Frames
    -0.07
     waged
    -0.07
    >To
    -0.07
     gracias
    -0.07
    .Ma
    -0.06
    embedding
    -0.06
     Bun
    -0.06
    syntax
    -0.06
    POSITIVE LOGITS
    ific
    0.06
    ژ
    0.06
    �
    0.06
     orn
    0.06
    ctl
    0.06
    ican
    0.06
    apeutics
    0.06
    什么
    0.06
    řád
    0.05
    (Class
    0.05
    Act Density 0.001%

    No Known Activations