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

    Neuronpedia

    INDEX
    Explanations

    Locations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     millennium
    -0.07
    ゲ
    -0.07
     ว
    -0.07
    .transaction
    -0.07
    ipment
    -0.06
     eve
    -0.06
     Kul
    -0.06
     Games
    -0.06
     بل
    -0.06
    TECTION
    -0.06
    POSITIVE LOGITS
     ре
    0.07
    ф
    0.06
    �
    0.06
     sloppy
    0.06
    ground
    0.06
     unsuccessful
    0.06
    paired
    0.06
    гар
    0.06
    /***
    0.06
     alphanumeric
    0.06
    Act Density 0.047%

    No Known Activations