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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hoop
    -0.06
     drifting
    -0.06
    angep
    -0.06
    POSIT
    -0.06
     कह
    -0.06
    quares
    -0.06
     game
    -0.06
     Ey
    -0.06
    iving
    -0.05
     تهیه
    -0.05
    POSITIVE LOGITS
     unstable
    0.07
    '.↵
    0.07
    _missing
    0.07
    .nb
    0.06
    .").
    0.06
     "");
↵
    0.06
    ')))
    0.06
     showdown
    0.06
     đoàn
    0.06
    -&
    0.06
    Act Density 0.025%

    No Known Activations