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

    Neuronpedia

    INDEX
    Explanations

    after

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     нових
    -0.07
    BTN
    -0.06
     [%
    -0.06
    Th
    -0.06
    deş
    -0.06
     کمتر
    -0.06
    ických
    -0.06
     unwilling
    -0.06
    compan
    -0.06
    Instead
    -0.06
    POSITIVE LOGITS
    rolley
    0.08
    //----------------------------------------------------------------------------↵
    0.07
    umat
    0.06
     Vendor
    0.06
    551
    0.06
     rarity
    0.06
    _samples
    0.06
     flavor
    0.06
    _allocate
    0.06
    urer
    0.06
    Act Density 0.007%

    No Known Activations