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

    Neuronpedia

    INDEX
    Explanations

    minus

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Point
    -0.07
     aquel
    -0.07
     примерно
    -0.07
    лась
    -0.06
    output
    -0.06
    /)↵
    -0.06
    _ac
    -0.06
    ;amp
    -0.06
     konut
    -0.06
     ово
    -0.06
    POSITIVE LOGITS
     LAND
    0.07
    VC
    0.06
     CAP
    0.06
     diagram
    0.06
     bab
    0.06
    ns
    0.06
    peer
    0.06
     rear
    0.06
     dns
    0.06
    ping
    0.06
    Act Density 0.000%

    No Known Activations