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

    Neuronpedia

    INDEX
    Explanations

    types of concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Tetra
    0.47
     antih
    0.46
     Gala
    0.45
     compacted
    0.45
     superfluid
    0.45
     discretization
    0.45
     Explosion
    0.45
     soup
    0.44
     Assassin
    0.44
     Intervention
    0.42
    POSITIVE LOGITS
    jquery
    0.50
    ue
    0.49
     potrebbero
    0.46
    sthe
    0.46
    isola
    0.46
    her
    0.45
    err
    0.45
    line
    0.45
    do
    0.44
    ctor
    0.43
    Act Density 0.004%

    No Known Activations