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

    Neuronpedia

    INDEX
    Explanations

    legal or technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GE
    0.50
    ODE
    0.49
     L
    0.46
    GO
    0.46
     Giant
    0.45
    tar
    0.44
     Gel
    0.44
    2
    0.43
    าล
    0.43
    Game
    0.43
    POSITIVE LOGITS
     artículos
    0.54
     orgull
    0.54
     оттен
    0.53
    rini
    0.52
     ensayos
    0.52
     experto
    0.51
     ativos
    0.51
     alrededores
    0.50
    templatemo
    0.50
     ésta
    0.50
    Act Density 0.005%

    No Known Activations