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

    Neuronpedia

    INDEX
    Explanations

    contractions and possessives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
      
    0.84
    ,
    0.81
     and
    0.73
    .
    0.70
     using
    0.70
     the
    0.69
     being
    0.67
    0.67
     (
    0.65
     be
    0.63
    POSITIVE LOGITS
    itabbam
    0.84
    keszt
    0.80
    neutrophiles
    0.79
    梘
    0.78
    itabbo
    0.78
    <unused49>
    0.78
    <unused65>
    0.77
    <unused69>
    0.77
    <unused29>
    0.77
    <unused88>
    0.76
    Act Density 0.361%

    No Known Activations