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

    Neuronpedia

    INDEX
    Explanations

    mathematical or code contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     melanch
    0.92
     Perspekt
    0.87
    ဂျ
    0.87
     psychedelic
    0.85
    <unused254>
    0.85
     perturbations
    0.85
     puer
    0.83
     provoke
    0.83
    رسٹ
    0.83
     sparsity
    0.82
    POSITIVE LOGITS
     поэтому
    0.90
    Anyway
    0.82
    blah
    0.78
      
    0.77
     (?)
    0.77
    (!)
    0.74
     (!)
    0.72
     therefore
    0.72
    ff
    0.71
    そのため
    0.71
    Act Density 0.634%

    No Known Activations