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

    Neuronpedia

    INDEX
    Explanations

    Caesar

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _ios
    -0.08
     Jardim
    -0.08
     دقيقة
    -0.08
    _condition
    -0.08
     Erika
    -0.08
    _conditions
    -0.08
     Lake
    -0.07
    Sdk
    -0.07
     nest
    -0.07
     Erit
    -0.07
    POSITIVE LOGITS
     Caesar
    0.10
     shifting
    0.09
     ciphertext
    0.09
    Postal
    0.08
     vowel
    0.08
     Shift
    0.08
     простой
    0.08
     ROT
    0.08
     foreground
    0.08
     nieuwsbrief
    0.08
    Act Density 0.001%

    No Known Activations