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

    Neuronpedia

    INDEX
    Explanations

    List of names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Quarter
    -0.07
     sacks
    -0.06
    (my
    -0.06
    �
    -0.06
    نة
    -0.06
     Appointment
    -0.06
    .Headers
    -0.06
    "N
    -0.06
     Combo
    -0.06
    献
    -0.06
    POSITIVE LOGITS
     Đào
    0.06
     (.
    0.06
    cene
    0.06
     """↵↵
    0.06
     Regions
    0.06
    นอ
    0.06
    recover
    0.06
     veřej
    0.06
    gricult
    0.06
    .setDescription
    0.06
    Act Density 0.031%

    No Known Activations