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

    Neuronpedia

    INDEX
    Explanations

    model

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     suggested
    0.45
     iterate
    0.43
    와의
    0.42
     атом
    0.41
     iteratively
    0.41
     ses
    0.40
     Continuation
    0.40
     sess
    0.40
     ay
    0.38
     draught
    0.38
    POSITIVE LOGITS
    ちゃん
    0.45
    ちゃんの
    0.40
    Mount
    0.40
    Hey
    0.39
     enggak
    0.39
    stateMutability
    0.38
    傌
    0.38
    덬
    0.38
    వర
    0.38
    गाव
    0.38
    Act Density 0.032%

    No Known Activations