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

    Neuronpedia

    INDEX
    Explanations

    generally compatible

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     piccoli
    0.51
     tecniche
    0.49
     joie
    0.47
     shitty
    0.45
     malade
    0.45
     grandi
    0.44
     dobbiamo
    0.44
    orderHint
    0.44
     deceduto
    0.44
     desolate
    0.43
    POSITIVE LOGITS
     International
    0.50
     Encyclopædia
    0.43
     benchmarks
    0.42
     Embassy
    0.41
     идентифика
    0.41
     Scripps
    0.40
     Shrine
    0.39
     OECD
    0.39
     Hispanic
    0.39
    ID
    0.39
    Act Density 0.001%

    No Known Activations