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

    Neuronpedia

    INDEX
    Explanations

    time before booking flights

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     instructive
    0.40
    힘
    0.39
    ன்க
    0.38
    ∝
    0.37
    RET
    0.37
    .&
    0.37
    nobyl
    0.37
    ]].
    0.36
    කර
    0.35
     RPA
    0.35
    POSITIVE LOGITS
     Fett
    0.41
     furrow
    0.40
    hemm
    0.40
     zee
    0.38
     Biggest
    0.38
     scum
    0.37
     zie
    0.37
    したり
    0.37
     thumbs
    0.37
     скоро
    0.36
    Act Density 0.000%

    No Known Activations