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

    Neuronpedia

    INDEX
    Explanations

    not a separate process

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tiredness
    0.44
     maxHeight
    0.43
    கர்
    0.43
     suppuration
    0.43
    ட்டால்
    0.42
     residues
    0.41
    狧
    0.41
     Weddings
    0.41
     breakage
    0.40
    çç
    0.40
    POSITIVE LOGITS
    r
    0.46
    STA
    0.42
    stm
    0.40
     সহজ
    0.39
    ren
    0.39
     necessari
    0.38
    ship
    0.37
     ferramenta
    0.37
    urb
    0.37
     strumento
    0.36
    Act Density 0.006%

    No Known Activations