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

    Neuronpedia

    INDEX
    Explanations

    foreign and russian words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     there
    0.54
     Brandy
    0.54
    ter
    0.52
     offered
    0.50
     Fire
    0.49
     Counsel
    0.47
     substance
    0.46
    there
    0.46
     Archaeology
    0.46
     Army
    0.45
    POSITIVE LOGITS
    FileNotFound
    0.47
     reduziert
    0.46
    霭
    0.44
    pinimg
    0.44
     kür
    0.44
     Stunden
    0.43
    üe
    0.42
    焗
    0.42
    доро
    0.42
    Paused
    0.42
    Act Density 0.000%

    No Known Activations