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

    Neuronpedia

    INDEX
    Explanations

    both

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     arou
    -0.07
    岁
    -0.07
     Testing
    -0.07
    eid
    -0.06
     ers
    -0.06
    ovní
    -0.06
    �
    -0.06
    高
    -0.06
     Economics
    -0.06
    ILT
    -0.06
    POSITIVE LOGITS
     both
    0.15
     Both
    0.13
    Both
    0.11
    both
    0.11
     BOTH
    0.09
     neither
    0.08
    _BOTH
    0.08
    .Co
    0.07
    _both
    0.07
     contraceptive
    0.07
    Act Density 0.047%

    No Known Activations