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

    Neuronpedia

    INDEX
    Explanations

    prompt instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     grower
    0.48
     farm
    0.48
     attorneys
    0.44
     attorney
    0.43
     husbandry
    0.42
     employer
    0.42
     homeowner
    0.41
    Church
    0.40
    Hull
    0.40
     breeder
    0.40
    POSITIVE LOGITS
     Malayalam
    0.50
    rufen
    0.48
     Shayari
    0.46
     BEFORE
    0.46
     +.
    0.44
     Methoden
    0.44
     Bhojpuri
    0.44
     ஸ்
    0.43
     shayari
    0.43
    ontaneous
    0.43
    Act Density 0.031%

    No Known Activations