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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    つの
    -0.07
    ตรง
    -0.07
    creation
    -0.07
     overcoming
    -0.06
    ลา
    -0.06
    esse
    -0.06
    worth
    -0.06
    塔
    -0.06
     amend
    -0.06
    洪
    -0.06
    POSITIVE LOGITS
    嘴
    0.07
    Amy
    0.07
    lazy
    0.06
     Naj
    0.06
     Echo
    0.06
    leveland
    0.06
     Dublin
    0.06
     الجديد
    0.06
    альну
    0.06
     Californ
    0.06
    Act Density 0.000%

    No Known Activations