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

    Neuronpedia

    INDEX
    Explanations

    word completions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     )$
    0.46
     dostup
    0.46
     для
    0.45
    verification
    0.45
    ({})
    0.44
    䈉
    0.43
     एक
    0.43
    solution
    0.42
    exerc
    0.42
    для
    0.42
    POSITIVE LOGITS
     bessere
    0.45
    ፈጥ
    0.43
    走出
    0.42
    Trib
    0.40
    ულის
    0.40
     hars
    0.40
     delve
    0.39
     Lately
    0.38
    arakat
    0.38
    Rus
    0.38
    Act Density 0.001%

    No Known Activations