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

    Neuronpedia

    INDEX
    Explanations

    dissolved

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    NSIndexPath
    -0.07
    腒
    -0.07
    utc
    -0.07
    🐍
    -0.07
    .dylib
    -0.07
    业余
    -0.07
     mAdapter
    -0.07
    ~↵
    -0.07
     Mus
    -0.07
     depth
    -0.07
    POSITIVE LOGITS
    integration
    0.07
     Consequently
    0.07
    .condition
    0.07
    	stage
    0.06
    イ
    0.06
     restrained
    0.06
    過來
    0.06
     transformed
    0.06
     WON
    0.06
     состоит
    0.06
    Act Density 0.009%

    No Known Activations