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

    Neuronpedia

    INDEX
    Explanations

    choosing to begin

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     reverted
    0.72
     உடன
    0.69
     reverts
    0.68
    を使用した
    0.65
    immediate
    0.65
    digos
    0.65
     Amended
    0.64
     immediate
    0.63
    むしろ
    0.62
     rejoined
    0.61
    POSITIVE LOGITS
    选择
    3.76
     choosing
    3.74
     choose
    3.67
    Choose
    3.55
     Choose
    3.55
    Choosing
    3.53
     Choosing
    3.51
    選擇
    3.51
    choose
    3.43
     chooses
    3.42
    Act Density 1.855%

    No Known Activations