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

    Neuronpedia

    INDEX
    Explanations

    lists, bullet points, definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :
    0.63
    /
    0.55
    +
    0.45
    ]+
    0.44
    +(
    0.43
     namesake
    0.43
     [(
    0.42
    [
    0.42
     kwal
    0.42
     ext
    0.41
    POSITIVE LOGITS
    计划
    0.49
    ন্নত
    0.46
    Gets
    0.45
     പരിച
    0.44
     계획
    0.44
    🤎
    0.43
    謢
    0.43
    byter
    0.42
    Plan
    0.42
     Boż
    0.41
    Act Density 0.002%

    No Known Activations