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

    Neuronpedia

    INDEX
    Explanations

    explaining management and consequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <0xC2>
    0.64
      
    0.59
     –
    0.57
    ,
    0.55
     and
    0.54
     (
    0.54
     red
    0.52
     to
    0.51
     "
    0.49
     for
    0.49
    POSITIVE LOGITS
    놁
    0.58
     située
    0.55
    迦
    0.52
    ópez
    0.51
     oublier
    0.50
    ेंगू
    0.49
    Según
    0.49
    ेलकम
    0.48
    Menurut
    0.47
    CONDUCT
    0.47
    Act Density 0.000%

    No Known Activations