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

    Neuronpedia

    INDEX
    Explanations

    macroscopic world

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     funcionario
    0.92
     방정
    0.81
     suing
    0.80
     提供
    0.80
     leads
    0.79
     proposent
    0.77
     recollect
    0.75
     网络
    0.74
     недели
    0.74
     logits
    0.74
    POSITIVE LOGITS
    }
    0.78
    ня
    0.76
    क
    0.74
    cambrian
    0.72
    judgment
    0.72
    compressible
    0.71
    ро
    0.71
    MERS
    0.70
    𝗷
    0.69
    ним
    0.68
    Act Density 0.001%

    No Known Activations