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

    Neuronpedia

    INDEX
    Explanations

    information about availability

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     OR
    0.49
     East
    0.45
     programmatic
    0.45
     catalyze
    0.45
    あるいは
    0.45
     accord
    0.44
     oppure
    0.43
     if
    0.42
     oder
    0.42
     Increasingly
    0.42
    POSITIVE LOGITS
    ”।
    0.47
    ка
    0.46
    су
    0.45
     मह
    0.45
    тра
    0.45
    тропо
    0.43
    タリア
    0.42
    க்குக
    0.42
    悴
    0.42
    者的
    0.42
    Act Density 0.004%

    No Known Activations