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

    Neuronpedia

    INDEX
    Explanations

    genes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ヵ
    -0.07
     lúc
    -0.07
     nevertheless
    -0.07
    (PC
    -0.07
     THEIR
    -0.07
     tę
    -0.06
     ther
    -0.06
    cil
    -0.06
     Auf
    -0.06
    微量
    -0.06
    POSITIVE LOGITS
    Recipient
    0.08
    .RGB
    0.07
     fencing
    0.07
    .SDK
    0.07
     privileges
    0.07
    GroupName
    0.07
    .student
    0.07
    ڛ
    0.07
     frag
    0.07
     exit
    0.07
    Act Density 0.019%

    No Known Activations