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

    Neuronpedia

    INDEX
    Explanations

    Encryption/decryption

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Fixture
    -0.06
     yours
    -0.06
    atherine
    -0.06
    imageName
    -0.06
     strife
    -0.06
     openness
    -0.06
     '"
    -0.06
     undeniable
    -0.06
    ベル
    -0.06
    primary
    -0.06
    POSITIVE LOGITS
     голов
    0.07
    710
    0.07
    Months
    0.06
     angl
    0.06
     Galactic
    0.06
    检测
    0.06
    -sign
    0.06
     Corporate
    0.06
    -gallery
    0.06
    فت
    0.06
    Act Density 0.005%

    No Known Activations