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

    Neuronpedia

    INDEX
    Explanations

    references to strategies and plans across various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    strategies for implementation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     moons
    -0.43
    Moons
    -0.42
     Rubber
    -0.41
    󠁮
    -0.41
     Coff
    -0.41
    󠁴
    -0.40
     INFL
    -0.40
    ochond
    -0.40
     rubber
    -0.40
    repaint
    -0.39
    POSITIVE LOGITS
     strategies
    1.49
     Strategies
    1.43
    Strategies
    1.38
    strategies
    1.36
     stratégies
    1.25
     estrategias
    1.20
     STRATEG
    0.94
    égias
    0.85
     techniques
    0.84
     strategie
    0.82
    Act Density 0.009%

    No Known Activations