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

    Neuronpedia

    INDEX
    Explanations

    relentless action or focus

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    u
    1.80
    j
    1.24
    i
    1.20
    d
    1.19
    a
    1.03
    _
    0.99
    ä
    0.90
    o
    0.86
    ere
    0.85
    ur
    0.85
    POSITIVE LOGITS
     relentless
    1.15
     ruthless
    1.14
     relentlessly
    0.98
     untouch
    0.90
    녕하십니까
    0.89
    วัสดี
    0.86
     merciless
    0.84
     compassion
    0.83
     be
    0.82
     tenía
    0.82
    Act Density 0.005%

    No Known Activations