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

    Neuronpedia

    INDEX
    Explanations

    prepositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Splitter
    -0.08
    Sampler
    -0.08
     worse
    -0.08
    以来
    -0.08
     worst
    -0.07
     terro
    -0.07
    OTES
    -0.07
    _SPL
    -0.07
     hotspots
    -0.07
     hemi
    -0.07
    POSITIVE LOGITS
     formatting
    0.10
    .format
    0.09
     answer
    0.09
     format
    0.09
     antwort
    0.09
     explanations
    0.09
    一句
    0.08
     reasoning
    0.08
     हिंदी
    0.08
     roman
    0.08
    Act Density 0.063%

    No Known Activations