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

    Neuronpedia

    INDEX
    Explanations

    Snake game properties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    墨西哥
    0.37
    Clusters
    0.37
    四
    0.36
    ēl
    0.36
    äne
    0.34
    三
    0.34
     സമ്
    0.33
    subplots
    0.33
     프린
    0.33
    딘
    0.33
    POSITIVE LOGITS
    කර
    0.35
     einsch
    0.34
     পারা
    0.34
     cobre
    0.34
     shaker
    0.33
    ispiele
    0.33
     கள
    0.33
     Allo
    0.32
     processes
    0.32
     চিহ্নিত
    0.32
    Act Density 0.003%

    No Known Activations