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

    Neuronpedia

    INDEX
    Explanations

    water and bacteria

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     undesired
    0.48
     intravascular
    0.47
     abuso
    0.47
     heps
    0.46
     injurious
    0.46
     cravings
    0.46
     impressively
    0.46
     undesirable
    0.46
     exportation
    0.45
     nguy
    0.45
    POSITIVE LOGITS
            
    0.51
     Tujuan
    0.50
     అలాగే
    0.50
     Derived
    0.50
     मकसद
    0.49
     Metrics
    0.47
     თქვენ
    0.46
        
    0.45
                            
    0.45
     Tools
    0.45
    Act Density 0.004%

    No Known Activations