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

    Neuronpedia

    INDEX
    Explanations

    years

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    InvalidOperationException
    -0.07
    탤
    -0.07
    .showToast
    -0.07
    _acc
    -0.07
    inely
    -0.07
     Spain
    -0.07
     rew
    -0.06
    医务
    -0.06
     fullname
    -0.06
    >\<^
    -0.06
    POSITIVE LOGITS
     chances
    0.07
     exchange
    0.07
     conspir
    0.07
    Instances
    0.06
    people
    0.06
    瞩目
    0.06
    书院
    0.06
    merge
    0.06
    .createCell
    0.06
    AST
    0.06
    Act Density 0.020%

    No Known Activations