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

    Neuronpedia

    INDEX
    Explanations

    liability

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     MOST
    -0.08
     června
    -0.08
    Laura
    -0.07
    flashdata
    -0.07
    Stone
    -0.07
     Zelda
    -0.07
     Laura
    -0.06
    called
    -0.06
    _ANY
    -0.06
     misinformation
    -0.06
    POSITIVE LOGITS
    kv
    0.08
     И
    0.07
     Minerals
    0.07
    lk
    0.06
     náklad
    0.06
    .fm
    0.06
    ithub
    0.06
    .by
    0.06
    lien
    0.06
     нали
    0.06
    Act Density 0.008%

    No Known Activations