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

    Neuronpedia

    INDEX
    Explanations

    ot

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     veřejné
    -0.08
     České
    -0.07
     الملك
    -0.06
     gubern
    -0.06
    loth
    -0.06
    .Invoke
    -0.06
     Tracker
    -0.06
    /sign
    -0.06
    องท
    -0.06
     Hop
    -0.06
    POSITIVE LOGITS
     Wish
    0.07
    _SYN
    0.06
    Granted
    0.06
     corners
    0.06
     interviewed
    0.06
     LayoutInflater
    0.06
     drip
    0.06
     inducing
    0.06
     disfr
    0.06
    óz
    0.06
    Act Density 0.021%

    No Known Activations