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

    Neuronpedia

    INDEX
    Explanations

    dwell

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     夏
    -0.06
     inputData
    -0.06
    ToLeft
    -0.06
    	Delete
    -0.06
    chi
    -0.06
    kud
    -0.06
    dsl
    -0.06
     melt
    -0.06
     Lond
    -0.06
    (test
    -0.06
    POSITIVE LOGITS
    standing
    0.06
     pcb
    0.06
    .addColumn
    0.06
     historically
    0.06
    escaping
    0.06
     Serbian
    0.06
    орт
    0.06
     phải
    0.06
     [/
    0.05
    (mask
    0.05
    Act Density 1.172%

    No Known Activations