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

    Neuronpedia

    INDEX
    Explanations

    that/this

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     older
    -0.07
     seab
    -0.06
    /to
    -0.06
     invoices
    -0.06
    reu
    -0.06
    ционные
    -0.06
    Je
    -0.06
     endoth
    -0.06
    ποιη
    -0.06
     �
    -0.06
    POSITIVE LOGITS
    πτωση
    0.07
    ansı
    0.07
    -focused
    0.07
     Amazing
    0.06
     MSS
    0.06
    ộc
    0.06
    _IV
    0.06
     uživatel
    0.06
    盒
    0.06
    考试
    0.06
    Act Density 0.168%

    No Known Activations