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

    Neuronpedia

    INDEX
    Explanations

    specific action followed by description

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    و
    0.51
    seeing
    0.50
     Você
    0.48
     majú
    0.47
    proces
    0.46
     SID
    0.46
    Mater
    0.46
     Spiel
    0.45
    Você
    0.45
    म
    0.45
    POSITIVE LOGITS
     молод
    0.44
     கார
    0.41
     ас
    0.41
     アー
    0.41
     дере
    0.41
     التلاميذ
    0.41
    elist
    0.40
     நோய்
    0.39
    }\\
    0.39
     стар
    0.39
    Act Density 0.012%

    No Known Activations