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

    Neuronpedia

    INDEX
    Explanations

    whether

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Tinder
    -0.07
    数量
    -0.06
     每
    -0.06
    ǎ
    -0.06
    -random
    -0.06
     Conditions
    -0.06
     dân
    -0.06
    <unsigned
    -0.06
     Roth
    -0.06
     updatedAt
    -0.06
    POSITIVE LOGITS
     pilgr
    0.07
    Shortcut
    0.07
     проф
    0.07
    iesta
    0.06
    디오
    0.06
    elling
    0.06
    ouncement
    0.06
    amax
    0.06
    ontrol
    0.06
     Handle
    0.06
    Act Density 0.009%

    No Known Activations