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

    Neuronpedia

    INDEX
    Explanations

    Sales, actions, deposition, verify

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ificance
    0.47
    ირი
    0.43
                        
    0.42
     score
    0.42
    ৫৮
    0.42
    ingredients
    0.42
     clicks
    0.41
    ING
    0.41
    TI
    0.41
                      
    0.40
    POSITIVE LOGITS
     müş
    0.50
     wikipagina
    0.50
     言っ
    0.46
     teoría
    0.46
     admi
    0.46
     문
    0.46
     gemüt
    0.45
     drewn
    0.45
     französischen
    0.45
     fér
    0.45
    Act Density 0.000%

    No Known Activations