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

    Neuronpedia

    INDEX
    Explanations

    I understand

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Streams
    0.36
    町村
    0.36
    雕
    0.35
    百貨
    0.35
    ps
    0.34
    uscular
    0.34
    lela
    0.34
     Baj
    0.34
    더라고
    0.33
     Pergamon
    0.33
    POSITIVE LOGITS
    George
    0.43
    Jorge
    0.43
    Kenneth
    0.42
    Kitchen
    0.40
     Kenneth
    0.40
     george
    0.40
     GEORGE
    0.38
    Gh
    0.37
    GEORGE
    0.37
     husk
    0.37
    Act Density 0.017%

    No Known Activations