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

    Neuronpedia

    INDEX
    Explanations

    flash cards

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    formulario
    0.40
     sentimiento
    0.40
     résult
    0.38
    ᴢ
    0.37
    itudes
    0.36
     출발
    0.36
    commend
    0.36
    TorpedoStore
    0.36
    俅
    0.36
     zaz
    0.36
    POSITIVE LOGITS
    脱
    0.45
     Prince
    0.43
    ристо
    0.42
     dangerous
    0.40
     nº
    0.40
    害
    0.40
     மாற்ற
    0.39
     опас
    0.39
    だけに
    0.38
    缪
    0.38
    Act Density 0.005%

    No Known Activations