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

    Neuronpedia

    INDEX
    Explanations

    JSON structure and keys

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    '=>'','
    0.81
     playthrough
    0.71
     doubt
    0.70
     added
    0.68
     skills
    0.68
    ただし
    0.68
    毫
    0.66
    ).</
    0.66
     reliance
    0.66
     però
    0.66
    POSITIVE LOGITS
    如下
    0.85
    ("""
    0.79
     =[
    0.77
    following
    0.75
     Orton
    0.75
    ('''
    0.74
    multline
    0.74
    以下
    0.72
    {
    0.71
     Becker
    0.71
    Act Density 0.369%

    No Known Activations