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

    Neuronpedia

    INDEX
    Explanations

    remote or deserted islands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Coelho
    0.88
    Rajas
    0.79
     Rajas
    0.79
     getline
    0.77
    Decoder
    0.75
     العاش
    0.74
     pct
    0.73
     Dharmendra
    0.73
     truckers
    0.73
     हरियाणा
    0.72
    POSITIVE LOGITS
     island
    3.38
     islands
    3.22
     Island
    3.03
    island
    2.78
    Island
    2.76
     Islands
    2.75
    岛
    2.65
     ISLAND
    2.64
     остров
    2.42
    島
    2.36
    Act Density 0.099%

    No Known Activations