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

    Neuronpedia

    INDEX
    Explanations

    say "year"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Abraham
    -0.07
     الاتحاد
    -0.07
     Isaiah
    -0.07
     quasi
    -0.07
    nya
    -0.07
    _det
    -0.06
    yard
    -0.06
     offspring
    -0.06
    公报
    -0.06
    桠
    -0.06
    POSITIVE LOGITS
     optic
    0.07
    latent
    0.07
    alink
    0.07
    hone
    0.07
    睇
    0.06
     Fires
    0.06
    ⻝
    0.06
    -loading
    0.06
    ircraft
    0.06
    ););↵
    0.06
    Act Density 0.029%

    No Known Activations