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

    Neuronpedia

    INDEX
    Explanations

    gold health contact understanding resistance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tend
    0.47
     Tend
    0.44
     tend
    0.43
    Tend
    0.42
    wiring
    0.42
     transport
    0.39
    transport
    0.38
    뷸
    0.36
    Transport
    0.36
     ይመ
    0.36
    POSITIVE LOGITS
     Gar
    0.50
     gar
    0.49
    Gar
    0.46
     Garo
    0.42
     Garcia
    0.41
     tràn
    0.39
    Garcia
    0.38
     Ashley
    0.38
     GAR
    0.38
     Robb
    0.38
    Act Density 0.000%

    No Known Activations