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

    Neuronpedia

    INDEX
    Explanations

    gradient id names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tentativo
    0.43
     Metadata
    0.40
    चा
    0.40
     SL
    0.39
     Spotify
    0.39
     Auf
    0.37
     वांछ
    0.37
     monolith
    0.37
     Slayer
    0.37
     NEAR
    0.37
    POSITIVE LOGITS
    名为
    0.51
    name
    0.45
    غي
    0.43
    名は
    0.43
     name
    0.42
    ்து
    0.41
    NAME
    0.41
    名を
    0.40
    checkable
    0.40
    ình
    0.38
    Act Density 0.000%

    No Known Activations