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

    Neuronpedia

    INDEX
    Explanations

    focusing on getting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Branch
    0.48
    The
    0.45
     Quận
    0.44
    Address
    0.42
     Contempor
    0.42
    Stage
    0.42
    Letter
    0.42
    Describe
    0.41
    ۔
    0.41
     बनाती
    0.41
    POSITIVE LOGITS
     intensifying
    0.54
     revanche
    0.50
     ಮತ್ತೆ
    0.49
    intai
    0.46
     kembali
    0.45
     выигра
    0.45
     reinvigor
    0.45
     myself
    0.43
    enses
    0.43
     როგორ
    0.43
    Act Density 0.006%

    No Known Activations