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

    Neuronpedia

    INDEX
    Explanations

    city before

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ter
    0.54
     offered
    0.51
    ться
    0.50
    িংস
    0.50
     there
    0.49
     Brandy
    0.47
     Fire
    0.47
     classmates
    0.46
     upward
    0.46
     substance
    0.44
    POSITIVE LOGITS
     reduziert
    0.49
     Stunden
    0.46
    pinimg
    0.45
    FBSDKError
    0.44
     دقیقه
    0.44
     Stunde
    0.44
    一台
    0.44
     втра
    0.43
    uko
    0.43
    靚
    0.43
    Act Density 0.000%

    No Known Activations