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

    Neuronpedia

    INDEX
    Explanations

    say ":"

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     “
    1.45
     “[
    1.44
     ".")
    1.41
     "")
    1.38
     ""}
    1.35
     “‘
    1.33
    "]="
    1.32
     “…
    1.28
    =”
    1.27
    ”?
    1.27
    POSITIVE LOGITS
    As
    1.16
    Severe
    1.10
    ::
    1.09
    Alert
    1.08
    Powerful
    1.06
    Here
    1.05
    Besides
    1.04
    Social
    1.02
    Start
    1.01
    Unlike
    1.01
    Act Density 0.003%

    No Known Activations