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

    Neuronpedia

    INDEX
    Explanations

    adjectives that convey intensity or uniqueness in experiences

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

    kinds of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    atiable
    -0.49
    gelopen
    -0.47
     Foire
    -0.46
     GLFW
    -0.45
    olyb
    -0.45
    endregion
    -0.45
     alertDialog
    -0.44
     blur
    -0.44
     Breakout
    -0.43
     maternidade
    -0.42
    POSITIVE LOGITS
    种
    1.27
    一种
    1.15
    種
    1.13
     种
    0.98
    一種
    0.94
    有一种
    0.93
    两种
    0.91
    几种
    0.89
    了一种
    0.89
    是一种
    0.86
    Act Density 0.002%

    No Known Activations