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

    Neuronpedia

    INDEX
    Explanations

    medical suffixes and units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    like
    0.38
    Assim
    0.35
    -
    0.35
     anillo
    0.34
     regimen
    0.33
    фіка
    0.33
    st
    0.33
    ifiant
    0.33
    volle
    0.33
    𝗲
    0.33
    POSITIVE LOGITS
    வர்களில்
    0.38
     UIApplication
    0.37
    _{
    0.37
    ^{
    0.35
    <unused35>
    0.34
    ూరు
    0.34
     ίδια
    0.34
     '"
    0.33
     perturbed
    0.32
    <0x10>
    0.32
    Act Density 0.000%

    No Known Activations