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

    Neuronpedia

    INDEX
    Explanations

    references to physical locations and structures

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

    low position, bottom, below

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    WithMany
    -0.47
     StringTokenizer
    -0.42
     سكانية
    -0.42
     bomber
    -0.41
    Дереккөздер
    -0.40
     balloon
    -0.40
     BoxFit
    -0.39
    Balloon
    -0.39
    balloon
    -0.38
     bougie
    -0.37
    POSITIVE LOGITS
     bajos
    0.70
     below
    0.69
     bottom
    0.68
     BOTTOM
    0.68
     rendah
    0.66
    below
    0.64
    lowest
    0.63
     abajo
    0.62
     low
    0.60
     inférieur
    0.60
    Act Density 0.325%

    No Known Activations