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

    Neuronpedia

    INDEX
    Explanations

    Gaining something

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (screen
    -0.07
     Many
    -0.07
     tops
    -0.07
     Ch
    -0.07
     Kaplan
    -0.07
    -sh
    -0.06
    ीज
    -0.06
     Kh
    -0.06
    Florida
    -0.06
     cpt
    -0.06
    POSITIVE LOGITS
     anthology
    0.07
    erture
    0.06
    良い
    0.06
    ayah
    0.06
     przez
    0.06
    .Substring
    0.06
    Malloc
    0.06
    .Generate
    0.06
    τηκε
    0.06
    がお
    0.06
    Act Density 1.711%

    No Known Activations