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

    Neuronpedia

    INDEX
    Explanations

    video

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     یافته
    -0.07
     BBB
    -0.07
     crates
    -0.06
    赞
    -0.06
     avoids
    -0.06
    ">%
    -0.06
    库
    -0.06
    erap
    -0.06
    	sum
    -0.06
     succ
    -0.06
    POSITIVE LOGITS
    .Dom
    0.07
     proving
    0.07
    _success
    0.06
     chiến
    0.06
    /log
    0.06
     dictate
    0.06
     savvy
    0.06
     ActiveRecord
    0.06
    .activ
    0.06
     tint
    0.06
    Act Density 0.029%

    No Known Activations