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

    Neuronpedia

    INDEX
    Explanations

    asset beta

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    েই
    0.46
    --){
    0.46
     অঞ্চলে
    0.46
     Од
    0.45
    ext
    0.45
     Ре
    0.45
     读取
    0.44
    ол
    0.44
     从
    0.44
     కూడా
    0.44
    POSITIVE LOGITS
    stimulating
    0.49
    zení
    0.46
     volition
    0.46
    텀
    0.45
    stimulation
    0.45
     dinn
    0.45
    hybrid
    0.44
    calorie
    0.43
     morgen
    0.43
     kalor
    0.43
    Act Density 0.003%

    No Known Activations