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

    Neuronpedia

    INDEX
    Explanations

    related to health

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    และความ
    0.43
     ਅਤੇ
    0.42
    Ⴌ
    0.42
     және
    0.41
     এবং
    0.41
    引起的
    0.41
    媑
    0.41
    urètre
    0.41
     நீர்
    0.40
    erà
    0.40
    POSITIVE LOGITS
    0.42
     be
    0.41
     sk
    0.40
     Sk
    0.37
     wed
    0.36
     division
    0.36
     stap
    0.36
     back
    0.36
     strateg
    0.36
     put
    0.36
    Act Density 0.004%

    No Known Activations