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

    Neuronpedia

    INDEX
    Explanations

    factor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ட்டை
    0.67
    astra
    0.66
    Proceed
    0.65
    ्युनिकेशन
    0.63
     அவ
    0.63
    ellipsis
    0.61
     命令
    0.61
     કરવાની
    0.60
    MemoryWarning
    0.59
    pias
    0.59
    POSITIVE LOGITS
     factors
    4.73
     Factors
    4.34
    factors
    4.21
    Factors
    4.07
     factores
    3.93
     factor
    3.74
     facteurs
    3.71
    因素
    3.70
     fatores
    3.64
     Faktoren
    3.62
    Act Density 1.433%

    No Known Activations