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

    Neuronpedia

    INDEX
    Explanations

    column references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Platforms
    0.43
     bureaus
    0.40
    platforms
    0.38
     cow
    0.38
    ADEM
    0.37
    cow
    0.37
    Cow
    0.37
    რება
    0.37
    ioides
    0.36
    Modules
    0.36
    POSITIVE LOGITS
     column
    1.43
     Column
    1.20
     columna
    1.20
    column
    1.17
     coluna
    1.14
    Column
    1.13
     kolom
    1.02
     COLUMN
    1.01
     колон
    0.98
     colonne
    0.95
    Act Density 0.024%

    No Known Activations