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

    Neuronpedia

    INDEX
    Explanations

    those

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Num
    -0.07
     marijuana
    -0.06
     Yup
    -0.06
    'es
    -0.06
     Julian
    -0.06
     研
    -0.06
     penet
    -0.06
     aden
    -0.06
    Pure
    -0.06
     lien
    -0.06
    POSITIVE LOGITS
    those
    0.07
     those
    0.07
     تلك
    0.06
    HAM
    0.06
     Caught
    0.06
    일본
    0.06
     spectator
    0.06
     그러
    0.06
     defe
    0.06
    ICH
    0.06
    Act Density 0.021%

    No Known Activations