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

    Neuronpedia

    INDEX
    Explanations

    spray paint and cans

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    in
    0.55
     Florida
    0.51
    AH
    0.51
    Florida
    0.50
    tens
    0.50
    AX
    0.49
    ;
    0.49
    electric
    0.48
    kinson
    0.48
    D
    0.48
    POSITIVE LOGITS
     sprays
    0.64
    ش
    0.64
     قيمة
    0.63
     relações
    0.61
     reeks
    0.61
    uées
    0.60
     філь
    0.59
     bruge
    0.59
    يريا
    0.59
     químico
    0.58
    Act Density 0.004%

    No Known Activations