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

    Neuronpedia

    INDEX
    Explanations

    haloes and galaxies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Mercury
    0.75
     Mercury
    0.74
     Filosof
    0.72
     matemat
    0.71
     Solaris
    0.71
     filosof
    0.70
    unar
    0.68
     Philosoph
    0.67
     Writes
    0.66
     philosopher
    0.65
    POSITIVE LOGITS
     Sloan
    0.77
     المص
    0.72
     haloes
    0.71
     आकाश
    0.71
     arm
    0.67
     tracers
    0.67
     halo
    0.67
     wealth
    0.63
     halos
    0.63
    Halo
    0.63
    Act Density 0.115%

    No Known Activations