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

    Neuronpedia

    INDEX
    Explanations

    numerals

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Level
    -0.07
     incurred
    -0.07
     Petite
    -0.07
    黎明
    -0.07
     Niet
    -0.06
    uge
    -0.06
     بك
    -0.06
    くなり
    -0.06
    ibox
    -0.06
     TensorFlow
    -0.06
    POSITIVE LOGITS
    וס
    0.07
    -direction
    0.07
    יית
    0.07
     Salisbury
    0.07
     실�
    0.07
     Explanation
    0.07
     formation
    0.07
    UpdatedAt
    0.07
    _wr
    0.07
     dfs
    0.07
    Act Density 0.039%

    No Known Activations