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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     generating
    -0.06
    ρύ
    -0.06
    Includes
    -0.06
     RC
    -0.06
    !)
    -0.06
    ))]
    -0.06
     informative
    -0.06
     RAM
    -0.06
    صه
    -0.06
     Hex
    -0.06
    POSITIVE LOGITS
    (use
    0.07
    Hair
    0.07
     neighb
    0.06
     dnů
    0.06
    (animated
    0.06
    (ierr
    0.06
    otřeb
    0.06
     uygulan
    0.06
     irgend
    0.06
     quil
    0.06
    Act Density 0.148%

    No Known Activations