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

    Neuronpedia

    INDEX
    Explanations

    Questions/Answers/Tests

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     recherchez
    -0.08
    pap
    -0.08
    Malloc
    -0.07
     macar
    -0.07
     humanitarian
    -0.07
    -0.07
     rechercher
    -0.07
    'ém
    -0.07
     tér
    -0.07
     tourists
    -0.07
    POSITIVE LOGITS
     утверж
    0.16
     FALSE
    0.15
     Aussagen
    0.14
     false
    0.14
     afirmar
    0.14
    真假
    0.14
     주장
    0.13
     False
    0.13
     falsely
    0.13
    False
    0.13
    Act Density 0.087%
    No Known Activations