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

    Neuronpedia

    INDEX
    Explanations

    probability calculations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sieve
    -0.07
    าม
    -0.07
     здоров
    -0.06
     anus
    -0.06
    _HANDLE
    -0.06
     TY
    -0.06
     `,
    -0.06
    　ﾊ
    -0.06
     يتم
    -0.06
    структор
    -0.06
    POSITIVE LOGITS
     mice
    0.07
    Delta
    0.06
     свід
    0.06
    ωμά
    0.06
    pdo
    0.06
     linear
    0.06
     nood
    0.06
     questi
    0.06
     Linear
    0.06
     revelations
    0.06
    Act Density 0.040%

    No Known Activations