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

    Neuronpedia

    INDEX
    Explanations

    introductions and clarifications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Vari
    0.55
    Vari
    0.55
    MIDI
    0.55
    vari
    0.54
    Features
    0.54
     Techniques
    0.53
    Ces
    0.52
    These
    0.51
    Ба
    0.51
     Compressor
    0.51
    POSITIVE LOGITS
     所以
    0.69
    罘
    0.63
     خواهد
    0.62
     yelled
    0.61
    ---’
    0.60
     將
    0.59
    iende
    0.59
     göra
    0.59
     atoi
    0.58
     라이
    0.58
    Act Density 0.109%

    No Known Activations