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

    Neuronpedia

    INDEX
    Explanations

    offering options or asking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    voegd
    0.80
    atering
    0.80
     notific
    0.79
     הער
    0.79
    oclonal
    0.79
    ⚠️
    0.76
     वाजिब
    0.76
     warnings
    0.76
     قابل
    0.74
     호출
    0.74
    POSITIVE LOGITS
     practicing
    1.52
     discuss
    1.48
     practice
    1.48
     explore
    1.47
     Discuss
    1.39
    Discuss
    1.38
     discussing
    1.36
    discuss
    1.32
     talk
    1.32
     practiced
    1.30
    Act Density 0.398%

    No Known Activations