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

    Neuronpedia

    INDEX
    Explanations

    Places

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Secretary
    -0.07
    guide
    -0.06
    aru
    -0.06
    227
    -0.06
     Sentry
    -0.06
     specifies
    -0.06
    HCI
    -0.06
     Frequ
    -0.06
     Aboriginal
    -0.06
     cocktails
    -0.06
    POSITIVE LOGITS
    .es
    0.07
     fueled
    0.07
    .At
    0.06
    Spain
    0.06
     віднов
    0.06
    �다
    0.06
    ’an
    0.06
    yntaxException
    0.06
     Spain
    0.06
    ').
    0.06
    Act Density 0.150%

    No Known Activations