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

    Neuronpedia

    INDEX
    Explanations

    trick question how many murderers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     équipements
    0.50
    更换
    0.42
     respectivement
    0.42
     pripre
    0.42
     pentru
    0.42
     odmah
    0.41
     instalação
    0.41
     cloning
    0.41
     fermeture
    0.41
     commandBuffer
    0.40
    POSITIVE LOGITS
    ?
    0.48
    త్
    0.43
    ۀ
    0.42
    ates
    0.42
    ural
    0.42
    ality
    0.42
    strel
    0.42
    nae
    0.42
    ных
    0.41
    ers
    0.40
    Act Density 0.004%

    No Known Activations