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

    Neuronpedia

    INDEX
    Explanations

    funny

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ியார்
    0.42
    HOB
    0.42
    ו
    0.42
    亚
    0.41
    риб
    0.40
    Rome
    0.40
     PAINE
    0.40
    EN
    0.40
    ToBounds
    0.40
     araştırm
    0.39
    POSITIVE LOGITS
    ようになりました
    0.49
     concurrently
    0.48
     refriger
    0.47
    もお
    0.46
     refrigerators
    0.44
     GPUs
    0.44
     zrozum
    0.43
     juggle
    0.42
     Schottky
    0.42
     nécessairement
    0.42
    Act Density 0.010%

    No Known Activations