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

    Neuronpedia

    INDEX
    Explanations

    levels

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Income
    -0.07
     busy
    -0.07
     Gul
    -0.07
     kommen
    -0.07
    �
    -0.06
    Young
    -0.06
     nye
    -0.06
    UGE
    -0.06
     merc
    -0.06
    ịch
    -0.06
    POSITIVE LOGITS
    /win
    0.08
     mixin
    0.06
    )i
    0.06
     قانون
    0.06
     VT
    0.06
    .cell
    0.06
    .apply
    0.06
    (request
    0.06
     lối
    0.06
     dáng
    0.06
    Act Density 0.000%

    No Known Activations