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

    Neuronpedia

    INDEX
    Explanations

    avenue q

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rafts
    0.40
    鞑
    0.37
    pf
    0.36
     constructing
    0.36
    ashed
    0.35
    হাসিক
    0.35
    fu
    0.34
     retreating
    0.34
     лет
    0.34
    koch
    0.34
    POSITIVE LOGITS
     Laptop
    0.45
    0.39
    ीजन
    0.38
     tablet
    0.38
     STRONG
    0.37
     Snapshot
    0.37
     laptop
    0.37
     Tablet
    0.37
    лее
    0.36
    ற்ப
    0.36
    Act Density 0.000%

    No Known Activations