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

    Neuronpedia

    INDEX
    Explanations

    naming and sound description

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    著
    0.55
    露
    0.48
     обосно
    0.45
    밂
    0.44
    托
    0.43
     небе
    0.43
    ैमर
    0.43
    留
    0.42
     Microbiol
    0.42
     корпора
    0.42
    POSITIVE LOGITS
    coverage
    0.53
    constant
    0.53
    riline
    0.51
     stinging
    0.50
    system
    0.50
    country
    0.49
    pipe
    0.49
     wagon
    0.49
     variance
    0.48
    day
    0.47
    Act Density 0.001%

    No Known Activations