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

    Neuronpedia

    INDEX
    Explanations

    State

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ᱔
    0.90
    િર
    0.88
    🥊
    0.85
     tämä
    0.84
     ফেরার
    0.84
     this
    0.83
     villagers
    0.82
     livros
    0.82
    ጲ
    0.81
     terkait
    0.81
    POSITIVE LOGITS
    State
    0.88
    റ്റ്
    0.77
    STATE
    0.76
    TYPE
    0.74
    state
    0.72
    colors
    0.72
     Consumption
    0.71
     State
    0.69
    ↵↵
    0.68
    barrel
    0.68
    Act Density 0.000%

    No Known Activations