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

    Neuronpedia

    INDEX
    Explanations

    link to licenses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     جاتے
    0.43
     শীত
    0.40
    MORDOR
    0.40
     முறையாக
    0.40
    quinoxalin
    0.40
    ക്കാരി
    0.39
     제공
    0.39
     പിന്നീട്
    0.38
    有利于
    0.38
     سرد
    0.38
    POSITIVE LOGITS
     ability
    0.42
     EPS
    0.40
     "
    0.40
     Ut
    0.40
     INTER
    0.38
    ];
    0.37
     "");
    0.37
    ]
    0.37
     R
    0.36
     effort
    0.36
    Act Density 0.000%

    No Known Activations