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

    Neuronpedia

    INDEX
    Explanations

    Informatica, earlier work, available

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RewardedVideo
    0.46
     speaker
    0.45
    speaker
    0.45
    伱
    0.42
    ayena
    0.42
    ፦
    0.41
    playlist
    0.41
     nobleman
    0.40
    ~(
    0.40
    ⇌
    0.40
    POSITIVE LOGITS
     earm
    0.48
     bags
    0.47
     trotzdem
    0.45
     store
    0.43
     bolsas
    0.43
     stora
    0.42
     papeles
    0.42
     organiz
    0.41
     dosta
    0.41
     offsets
    0.41
    Act Density 0.005%

    No Known Activations