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

    Neuronpedia

    INDEX
    Explanations

    phrases related to problem-solving and figuring things out

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

    figure out

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ene
    -0.39
     Goldsmith
    -0.36
     dedicated
    -0.36
     media
    -0.35
     Rare
    -0.35
     Shield
    -0.34
     refreshing
    -0.34
     har
    -0.34
     products
    -0.33
     biomass
    -0.33
    POSITIVE LOGITS
     figuring
    1.02
     figured
    0.81
     NSCoder
    0.74
    +#+#
    0.72
    figure
    0.71
    figured
    0.69
     figure
    0.68
    SequentialGroup
    0.67
     averiguar
    0.66
    setVerticalGroup
    0.66
    Act Density 0.010%

    No Known Activations