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

    Neuronpedia

    INDEX
    Explanations

    not having Google search

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     will
    0.39
     Sand
    0.39
     A
    0.38
     can
    0.36
     The
    0.35
     There
    0.35
     estrogen
    0.35
     Pearson
    0.34
     Salt
    0.34
     They
    0.34
    POSITIVE LOGITS
     btw
    0.61
     😉
    0.55
     ;)
    0.55
    rasında
    0.55
    !”,
    0.54
    !")
    0.54
    !!”
    0.51
    😉
    0.51
    btw
    0.50
    !”
    0.50
    Act Density 0.032%

    No Known Activations