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

    Neuronpedia

    INDEX
    Explanations

    email headers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ètre
    -0.07
    CLS
    -0.06
    eti
    -0.06
    optimized
    -0.06
    แจ
    -0.06
    iting
    -0.06
     UC
    -0.06
    HAM
    -0.06
    ีย
    -0.06
    HA
    -0.06
    POSITIVE LOGITS
     підстав
    0.07
                               ↵
    0.07
     nhắc
    0.06
     ");
↵
    0.06
     colspan
    0.06
     strstr
    0.06
    )');↵
    0.06
    minecraft
    0.06
     Davidson
    0.06
    .');↵
    0.06
    Act Density 0.003%

    No Known Activations