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

    Neuronpedia

    INDEX
    Explanations

    code snippets and technical discussions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .zoom
    -0.08
    ування
    -0.07
     arrogant
    -0.07
    .dismiss
    -0.07
     보면
    -0.07
     حداقل
    -0.06
     streak
    -0.06
    ampilkan
    -0.06
     ENUM
    -0.06
     आख
    -0.06
    POSITIVE LOGITS
    」↵
    0.07
    /common
    0.06
    чук
    0.06
    vd
    0.06
    nature
    0.06
    atin
    0.06
    구
    0.06
    "]↵↵
    0.05
     Nej
    0.05
    ぇ
    0.05
    Act Density 0.000%

    No Known Activations