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

    Neuronpedia

    INDEX
    Explanations

    explanatory phrases that involve the word "is" followed by "that"

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

    because

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    /**
    -0.48
    creens
    -0.47
     незавершена
    -0.47
    MethodManager
    -0.46
    სქოლიო
    -0.46
     valmis
    -0.46
    AnchorStyles
    -0.44
    :✨
    -0.44
    ttemberg
    -0.43
     conosco
    -0.43
    POSITIVE LOGITS
     because
    0.98
    because
    0.84
    因为
    0.80
     porque
    0.80
    Because
    0.77
     BECAUSE
    0.77
     Because
    0.76
     Porque
    0.73
    Porque
    0.72
     karena
    0.71
    Act Density 0.028%

    No Known Activations