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

    Neuronpedia

    INDEX
    Explanations

    123

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     KM
    -0.08
    cky
    -0.07
    'H
    -0.07
    �
    -0.07
    -view
    -0.07
     yolu
    -0.06
    Prog
    -0.06
    .issue
    -0.06
    zilla
    -0.06
     Y
    -0.06
    POSITIVE LOGITS
    ':['
    0.08
    /↵↵↵↵
    0.07
     найб
    0.07
     creation
    0.07
    }')↵↵
    0.06
     Lopez
    0.06
    %%↵
    0.06
     faithfully
    0.06
    .Are
    0.06
     Secret
    0.06
    Act Density 0.018%

    No Known Activations