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

    Neuronpedia

    INDEX
    Explanations

    is/was followed by descriptive phrase

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     conocidas
    0.43
     కృషి
    0.40
     Cliquez
    0.40
     economically
    0.40
    巡
    0.40
    స్తోంది
    0.39
     significativa
    0.38
     språk
    0.38
    ípio
    0.38
    进来
    0.38
    POSITIVE LOGITS
    Used
    0.52
     utilised
    0.49
     used
    0.48
     Used
    0.48
    used
    0.48
    Spect
    0.47
     indispensable
    0.47
     employed
    0.46
    MVP
    0.45
     MVP
    0.45
    Act Density 0.001%

    No Known Activations