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

    Neuronpedia

    INDEX
    Explanations

    Meta-learning learn to learn

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    },\
    0.52
     pemeriksaan
    0.51
    illin
    0.50
     quería
    0.49
    }.
    0.49
    ilig
    0.48
    igger
    0.48
    ährung
    0.48
    ihar
    0.47
     คํา
    0.47
    POSITIVE LOGITS
     डॉ
    0.53
     Ευ
    0.52
    lerce
    0.51
     Є
    0.48
     ग्रुप
    0.48
     Tukey
    0.47
    ==============]
    0.47
    veis
    0.47
     Disse
    0.47
     tacky
    0.46
    Act Density 0.002%

    No Known Activations