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

    Neuronpedia

    INDEX
    Explanations

    until, endlessly, relentlessly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ία
    0.41
    ǯ
    0.38
    ᴿ
    0.38
     chen
    0.37
     explicit
    0.37
     ∂
    0.37
     PRI
    0.36
    ற்றம்
    0.36
    oiden
    0.36
    保
    0.36
    POSITIVE LOGITS
     merciless
    0.73
    จน
    0.70
     hasta
    0.70
     till
    0.66
     relentlessly
    0.65
     endlessly
    0.65
     senseless
    0.64
     until
    0.64
     עד
    0.63
     incessantly
    0.63
    Act Density 0.016%

    No Known Activations