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

    Neuronpedia

    INDEX
    Explanations

    first name last name

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    _
    0.61
     s
    0.60
     good
    0.60
     real
    0.59
     e
    0.58
    e
    0.57
     high
    0.55
    ,
    0.55
     out
    0.55
     per
    0.55
    POSITIVE LOGITS
    <unused1167>
    0.86
    <unused1000>
    0.85
    ujjati
    0.83
    oniazid
    0.82
    abhavena
    0.81
    <unused1053>
    0.79
    neutrophiles
    0.78
    ómago
    0.78
    运用
    0.78
    abhave
    0.78
    Act Density 0.035%

    No Known Activations