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

    Neuronpedia

    INDEX
    Explanations

    suitable or worthy things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Ст
    0.37
     thereof
    0.35
    /
    0.35
     confers
    0.35
    Firstly
    0.35
     entails
    0.34
    ox
    0.34
    Appear
    0.34
    ?),
    0.34
     zuerst
    0.33
    POSITIVE LOGITS
    เหมาะ
    0.71
     worthy
    0.64
     เหมาะ
    0.62
    讓你
    0.60
     достой
    0.60
    适合
    0.60
    值得
    0.59
     поможет
    0.59
    让你
    0.57
     suitable
    0.57
    Act Density 0.014%

    No Known Activations