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

    Neuronpedia

    INDEX
    Explanations

    let's start with some

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Efter
    0.77
    Good
    0.75
     ця
    0.75
     કરશે
    0.74
    गुड
    0.72
    İlk
    0.69
    Mental
    0.68
    Très
    0.68
    Parks
    0.67
     ziy
    0.67
    POSITIVE LOGITS
    可以通过
    0.66
     thatch
    0.66
     alchemy
    0.64
    ie
    0.64
    น์
    0.64
    u
    0.64
    spy
    0.62
    asign
    0.62
    〢
    0.61
    ที
    0.61
    Act Density 0.001%

    No Known Activations